Streaming language models
Language models that support streaming responses. See https://replicate.com/docs/streaming
Recommended models
![](https://tjzk.replicate.delivery/models_models_featured_image/779f3f58-c3db-4403-a01b-3ffed97a1449/out-0-1.jpg)
bytedance/sdxl-lightning-4step
SDXL-Lightning by ByteDance: a fast text-to-image model that makes high-quality images in 4 steps
![](https://tjzk.replicate.delivery/models_models_featured_image/3dcb020b-1fad-4101-84cf-88af9b20ac21/meta-logo.png)
meta/meta-llama-3-70b-instruct
A 70 billion parameter language model from Meta, fine tuned for chat completions
![](https://tjzk.replicate.delivery/models_models_featured_image/68b7dc1a-4767-4353-b066-212b0126b5de/meta-logo.png)
meta/meta-llama-3-8b-instruct
An 8 billion parameter language model from Meta, fine tuned for chat completions
![](https://tjzk.replicate.delivery/models_models_cover_image/dd9ac11a-edda-4d33-b413-6a721c44dfb0/meta-logo.png)
meta/meta-llama-3-8b
Base version of Llama 3, an 8 billion parameter language model from Meta.
![](https://tjzk.replicate.delivery/models_models_featured_image/454548d6-4978-4d85-bca3-d067dfc031bf/llava.png)
yorickvp/llava-13b
Visual instruction tuning towards large language and vision models with GPT-4 level capabilities
![](https://tjzk.replicate.delivery/models_models_featured_image/b9867b79-28e4-4e8f-b2b3-0f669111869c/mixtral.png)
mistralai/mixtral-8x7b-instruct-v0.1
The Mixtral-8x7B-instruct-v0.1 Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts tuned to be a helpful assistant.
![](https://tjzk.replicate.delivery/models_models_featured_image/e18de70b-6147-4d42-a730-4777d297737d/llama-logo.png)
meta/llama-2-7b-chat
A 7 billion parameter language model from Meta, fine tuned for chat completions
![](https://tjzk.replicate.delivery/models_models_featured_image/70238cb4-e24b-43ed-96e0-5f7d98f9cc3f/future-llama-70b-chat.jpg)
meta/llama-2-70b-chat
A 70 billion parameter language model from Meta, fine tuned for chat completions
![](https://tjzk.replicate.delivery/models_models_featured_image/e3fa9c03-7993-49d1-b6f3-351ead5e5dfc/high_tech_llama.png)
meta/llama-2-13b-chat
A 13 billion parameter language model from Meta, fine tuned for chat completions
![](https://tjzk.replicate.delivery/models_models_cover_image/7553cbf4-563d-4140-a51d-7386b8d13941/mistral-7b-instruct-cover.png)
mistralai/mistral-7b-instruct-v0.2
The Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an improved instruct fine-tuned version of Mistral-7B-Instruct-v0.1.
![](https://tjzk.replicate.delivery/models_models_cover_image/341d1fb8-9d72-4d9b-9fc7-b1a29ad85bcd/db72a8f8-759b-48db-8f18-316cd632.webp)
yorickvp/llava-v1.6-vicuna-13b
LLaVA v1.6: Large Language and Vision Assistant (Vicuna-13B)
![](https://tjzk.replicate.delivery/models_models_cover_image/6bc7974c-7209-4877-98f5-23e77ef1c6da/fa58799b-aa47-4117-bf1f-25149e2d.webp)
yorickvp/llava-v1.6-mistral-7b
LLaVA v1.6: Large Language and Vision Assistant (Mistral-7B)
![](https://tjzk.replicate.delivery/models_models_cover_image/1c8604e3-fc58-4dd6-b2ff-337ab396df7c/fofr_two_friendly_3d_characters_a.png)
fofr/prompt-classifier
Determines the toxicity of text to image prompts, llama-13b fine-tune. [SAFETY_RANKING] between 0 (safe) and 10 (toxic)
![](https://tjzk.replicate.delivery/models_models_cover_image/c56ddfb4-2193-4a65-862b-c274da78f07d/mistral7b_image2.jpeg)
mistralai/mistral-7b-v0.1
A 7 billion parameter language model from Mistral.
![](https://tjzk.replicate.delivery/models_models_cover_image/c6163ba0-edfc-4b53-9a23-eab7fd08b28a/b14df1cd-2e49-4e6b-b965-0deea7c1.webp)
yorickvp/llava-v1.6-34b
LLaVA v1.6: Large Language and Vision Assistant (Nous-Hermes-2-34B)
replicate-internal/llama-2-70b-triton
![](https://tjzk.replicate.delivery/models_models_featured_image/859c8ec6-4046-4d4e-9826-b7b575e5b79f/cover.webp)
fofr/latent-consistency-model
Super-fast, 0.6s per image. LCM with img2img, large batching and canny controlnet
![](https://tjzk.replicate.delivery/models_models_featured_image/ad668055-b12b-4f67-92a7-62e9c2f87df7/mistral7b_image1.jpeg)
mistralai/mistral-7b-instruct-v0.1
An instruction-tuned 7 billion parameter language model from Mistral
![](https://tjzk.replicate.delivery/models_models_featured_image/793e32b4-913c-4036-a847-4afb38e42fc1/Snowflake_Arctic_Opengraph_120.png)
snowflake/snowflake-arctic-instruct
An efficient, intelligent, and truly open-source language model
![](https://tjzk.replicate.delivery/models_models_cover_image/8b3db5d5-a4de-4271-b7b2-d511672452e1/out-0.png)
meta/llama-2-7b
Base version of Llama 2 7B, a 7 billion parameter language model
![](https://tjzk.replicate.delivery/models_models_featured_image/bb398430-da26-49ef-aefc-283212538c39/dolly_sheep2.jpg)
replicate/dolly-v2-12b
An open source instruction-tuned large language model developed by Databricks
![](https://tjzk.replicate.delivery/models_models_cover_image/c5881b08-9e53-4c3f-a8c9-80acdf2dffff/out-0_15-04.jpeg)
spuuntries/flatdolphinmaid-8x7b-gguf
Undi95's FlatDolphinMaid 8x7B Mixtral Merge, GGUF Q5_K_M quantized by TheBloke.
![](https://tjzk.replicate.delivery/models_models_cover_image/8e044b4c-0b20-4717-83bd-a94d89fb0dbe/meta-logo.png)
meta/meta-llama-3-70b
Base version of Llama 3, a 70 billion parameter language model from Meta.
![](https://tjzk.replicate.delivery/models_models_cover_image/a0fc9796-540f-4a31-ae81-1fe19bb22c96/llama_herd.png)
meta/llama-2-70b
Base version of Llama 2, a 70 billion parameter language model from Meta.
![](https://tjzk.replicate.delivery/models_models_cover_image/14b4060f-cb59-4b2a-987a-0cc4be5229e4/lavis-logo.png)
joehoover/instructblip-vicuna13b
An instruction-tuned multi-modal model based on BLIP-2 and Vicuna-13B
![](https://tjzk.replicate.delivery/models_models_featured_image/b2b74ffa-1b41-4b80-a210-11a996f0a4b0/yi_thumbnail_1.png)
01-ai/yi-34b-chat
The Yi series models are large language models trained from scratch by developers at 01.AI.
![](https://tjzk.replicate.delivery/models_models_featured_image/e90f0bd4-10f1-4317-9e42-fbf76224e950/robot_llama.png)
replicate/vicuna-13b
A large language model that's been fine-tuned on ChatGPT interactions
![](https://tjzk.replicate.delivery/models_models_cover_image/41b3c601-cc8b-437f-ab60-297037a364a1/goliath.png)
nateraw/goliath-120b
An auto-regressive causal LM created by combining 2x finetuned Llama-2 70B into one.
andreasjansson/sheep-duck-llama-2-70b-v1-1-gguf
![](https://tjzk.replicate.delivery/models_models_cover_image/77764656-b253-4f6a-a666-52b560312695/ideogram.jpg)
meta/llama-2-13b
Base version of Llama 2 13B, a 13 billion parameter language model
antoinelyset/openhermes-2-mistral-7b-awq
![](https://tjzk.replicate.delivery/models_models_cover_image/d08ef0b6-2b80-491a-984a-d4287d6325c0/yi_thumbnail.png)
01-ai/yi-6b
The Yi series models are large language models trained from scratch by developers at 01.AI.
![](https://tjzk.replicate.delivery/models_models_featured_image/8186a063-0dc9-41eb-a941-3dc6dd9a14fc/flan.png)
replicate/flan-t5-xl
A language model by Google for tasks like classification, summarization, and more
![](https://tjzk.replicate.delivery/models_models_cover_image/aac9e52d-b191-4fb2-862a-b2bd6341fabc/large-2.png)
meta/codellama-34b-instruct
A 34 billion parameter Llama tuned for coding and conversation
![](https://tjzk.replicate.delivery/models_models_featured_image/da89abc2-ef27-40c3-b6b1-f9877949a35e/codellama.jpg)
meta/codellama-13b
A 13 billion parameter Llama tuned for code completion
![](https://tjzk.replicate.delivery/models_models_featured_image/12546857-d49a-4fd9-873f-14dd9800ddf8/mascot.png)
stability-ai/stablelm-tuned-alpha-7b
7 billion parameter version of Stability AI's language model
![](https://tjzk.replicate.delivery/models_models_featured_image/a2541b38-6df1-4fa5-9485-9b3068502515/space_llama.png)
replicate/llama-7b
Transformers implementation of the LLaMA language model
![](https://tjzk.replicate.delivery/models_models_cover_image/3cbb4e68-08b8-4e82-8e83-3300f877dd0f/moondream2.png)
lucataco/moondream2
moondream2 is a small vision language model designed to run efficiently on edge devices
![](https://tjzk.replicate.delivery/models_models_cover_image/cbbad8a6-8be9-4496-9ebe-bf57fb3a3496/openchat_image_2.png)
nateraw/openchat_3.5-awq
OpenChat: Advancing Open-source Language Models with Mixed-Quality Data
![](https://tjzk.replicate.delivery/models_models_cover_image/1b5053da-932d-4e62-b957-f9f33d166902/gemma.jpg)
google-deepmind/gemma-2b-it
2B instruct version of Google’s Gemma model
![](https://tjzk.replicate.delivery/models_models_cover_image/fd1da3ea-a71e-4f5c-a996-642325de3912/microsoft.webp)
lucataco/phi-3-mini-4k-instruct
Phi-3-Mini-4K-Instruct is a 3.8B parameters, lightweight, state-of-the-art open model trained with the Phi-3 datasets
![](https://tjzk.replicate.delivery/models_models_cover_image/882c64df-8036-4d45-bab9-151a7c2f9350/orcas.png)
nateraw/mistral-7b-openorca
Mistral-7B-v0.1 fine tuned for chat with the OpenOrca dataset.
![](https://tjzk.replicate.delivery/models_models_featured_image/d2f84619-a92c-41ab-a88d-10faf493a0f4/gemma.jpg)
google-deepmind/gemma-7b-it
7B instruct version of Google’s Gemma model
![](https://tjzk.replicate.delivery/models_models_cover_image/ee2669a2-ebc5-4f3b-8365-9a3790050adb/nous-hermes-2.png)
nateraw/nous-hermes-2-solar-10.7b
Nous Hermes 2 - SOLAR 10.7B is the flagship Nous Research model on the SOLAR 10.7B base model..
![](https://tjzk.replicate.delivery/models_models_cover_image/fdb46cbf-1889-49c9-862c-4aac97bb2372/3054e464-d9ab-466b-8567-8cca87ad.webp)
yorickvp/llava-v1.6-vicuna-7b
LLaVA v1.6: Large Language and Vision Assistant (Vicuna-7B)
![](https://tjzk.replicate.delivery/models_models_cover_image/e8f484a0-8859-4fe3-b3a7-6f77c6f5e658/mplug-owl-logo.png)
joehoover/mplug-owl
An instruction-tuned multimodal large language model that generates text based on user-provided prompts and images
![](https://tjzk.replicate.delivery/models_models_cover_image/5a154e95-ab52-434c-b938-9a23b87cd796/FrDAYheWcAA3g4V.png)
fofr/image-prompts
Generate image prompts for Midjourney. Prefix inputs with "Image: "
![](https://tjzk.replicate.delivery/models_models_cover_image/88e08650-ebbe-4440-9dbd-c790580ac548/medium-1.png)
meta/codellama-13b-instruct
A 13 billion parameter Llama tuned for coding and conversation
![](https://tjzk.replicate.delivery/models_models_featured_image/5a378594-e982-4fb5-a30e-0524edf1d64a/replicate-prediction-7unwtpjbd.png)
joehoover/falcon-40b-instruct
A 40 billion parameter language model trained to follow human instructions.
![](https://tjzk.replicate.delivery/models_models_cover_image/f729aa1f-e9a9-463f-b6b0-756593ca4f1a/small-6.png)
meta/codellama-7b-instruct
A 7 billion parameter Llama tuned for coding and conversation
![](https://tjzk.replicate.delivery/models_models_cover_image/dc842381-8d67-4920-8721-d854958c5071/dolphin.png)
kcaverly/dolphin-2.5-mixtral-8x7b-gguf
Mixtral-8x7b MOE model trained for chat with the dolphin dataset, quantized
![](https://tjzk.replicate.delivery/models_models_cover_image/67eed8a1-ba88-4251-89b3-a8b05bc225f1/nice-robot.png)
replicate/oasst-sft-1-pythia-12b
An open source instruction-tuned large language model developed by Open-Assistant
![](https://tjzk.replicate.delivery/models_models_cover_image/58fbaec2-f855-4b83-99ab-5ead931e05cb/dolphin.png)
lucataco/dolphin-2.2.1-mistral-7b
Mistral-7B-v0.1 fine tuned for chat with the Dolphin dataset (an open-source implementation of Microsoft's Orca)
![](https://tjzk.replicate.delivery/models_models_cover_image/763769a0-5198-4100-81c0-3bac94017636/openchat.png)
kcaverly/openchat-3.5-1210-gguf
The "Overall Best Performing Open Source 7B Model" for Coding + Generalization or Mathematical Reasoning
![](https://tjzk.replicate.delivery/models_models_cover_image/88312caa-17c6-4ef7-81f0-7d2355d715fd/sqlcoder-7b-2.webp)
nateraw/defog-sqlcoder-7b-2
A capable large language model for natural language to SQL generation.
![](https://tjzk.replicate.delivery/models_models_cover_image/e49d5162-28ad-435a-af87-030d135b79e1/replicate-prediction-5eouup3b67bn.png)
andreasjansson/codellama-7b-instruct-gguf
CodeLlama-7B-instruct with support for grammars and jsonschema
![](https://tjzk.replicate.delivery/models_models_featured_image/376ecb38-3aa9-4848-9209-c19fc09de0e2/Kfbsjaw1IfqEQkc6NZFbr03PHKjEZe.png)
meta/codellama-70b-instruct
A 70 billion parameter Llama tuned for coding and conversation
![](https://tjzk.replicate.delivery/models_models_cover_image/a788f9b7-490c-48a3-b843-e0270274ba76/1690740835_3.png)
uwulewd/airoboros-llama-2-70b
Inference Airoboros L2 70B 2.1 - GPTQ using ExLlama.
![](https://tjzk.replicate.delivery/models_models_cover_image/c6bb2c34-8ad9-4c2b-a7d8-3252b2f17733/wizard.webp)
lucataco/wizardcoder-33b-v1.1-gguf
WizardCoder: Empowering Code Large Language Models with Evol-Instruct
replicate/lifeboat-70b
![](https://tjzk.replicate.delivery/models_models_cover_image/19000ca4-fd91-40f2-86cc-41ca62d1ce83/small-4.png)
meta/codellama-7b
A 7 billion parameter Llama tuned for coding and conversation
![](https://tjzk.replicate.delivery/models_models_cover_image/e6a761e7-49c9-4012-bd3e-6e5e8fea9352/replicate-prediction-gtkjtzlbv5kz.png)
nomagick/chatglm3-6b
A 6B parameter open bilingual chat LLM | 开源双语对话语言模型
![](https://tjzk.replicate.delivery/models_models_cover_image/6b8951ad-e5b7-407f-9ecd-96a998ca8844/output-01.jpeg)
spuuntries/miqumaid-v1-70b-gguf
NeverSleep's MiquMaid v1 70B Miqu Finetune, GGUF Q3_K_M quantized by NeverSleep.
![](https://tjzk.replicate.delivery/models_models_cover_image/0c37e013-0733-4c2e-8bae-ae8b38689d47/sqlcoder_image_2.png)
gregwdata/defog-sqlcoder-q8
Defog's SQLCoder is a state-of-the-art LLM for converting natural language questions to SQL queries. SQLCoder is a 15B parameter fine-tuned on a base StarCoder model.
![](https://tjzk.replicate.delivery/models_models_cover_image/5f0a161a-2a4d-485a-9f7a-f90e2daffbf8/dolphin.png)
lucataco/dolphin-2.1-mistral-7b
Mistral-7B-v0.1 fine tuned for chat with the Dolphin dataset (an open-source implementation of Microsoft's Orca)
![](https://tjzk.replicate.delivery/models_models_cover_image/9dfae179-a621-46b2-a305-116d5ce71a0e/replicate-prediction-ahgs27rx31rg.png)
lucataco/wizard-vicuna-13b-uncensored
This is wizard-vicuna-13b trained with a subset of the dataset - responses that contained alignment / moralizing were removed
![](https://tjzk.replicate.delivery/models_models_cover_image/e09f88b3-ac0b-4a76-9865-0252f705d5a0/neural_beagle.png)
kcaverly/neuralbeagle14-7b-gguf
NeuralBeagle14-7B is (probably) the best 7B model you can find!
antoinelyset/openhermes-2.5-mistral-7b
![](https://tjzk.replicate.delivery/models_models_cover_image/4228bfbc-bcb7-404d-8586-726c31f7073c/kqm9ddydl8_1689082483825.png)
nomagick/chatglm2-6b
ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型
![](https://tjzk.replicate.delivery/models_models_cover_image/38f48931-c374-42ce-abce-46af276f675e/replicate-prediction-xljpyblbcoee.png)
lucataco/moondream1
(Research only) Moondream1 is a vision language model that performs on par with models twice its size
![](https://tjzk.replicate.delivery/models_models_cover_image/e3de609c-6a60-4481-b6e3-57e0b00e4487/large-3.png)
meta/codellama-34b
A 34 billion parameter Llama tuned for coding and conversation
![](https://tjzk.replicate.delivery/models_models_cover_image/44b97533-9749-44c6-bea9-2e50b5527174/eleuther-ai-logo.png)
replicate/gpt-j-6b
A large language model by EleutherAI
![](https://tjzk.replicate.delivery/models_models_cover_image/1f2b3f7a-e583-43db-9f9c-a363c167e5df/hermes.png)
kcaverly/nous-hermes-2-yi-34b-gguf
Nous Hermes 2 - Yi-34B is a state of the art Yi Fine-tune, fine tuned on GPT-4 generated synthetic data
![](https://tjzk.replicate.delivery/models_models_cover_image/19f28529-a6cf-40e5-a534-9ba97837f92f/replicate-prediction-nb6c4m3bgvmt.png)
andreasjansson/llama-2-13b-chat-gguf
Llama-2 13B chat with support for grammars and jsonschema
![](https://tjzk.replicate.delivery/models_models_cover_image/e80a5ad6-9efa-446b-bed4-c17ea1e4713b/robot_writer.png)
replicate/mpt-7b-storywriter
A 7B parameter LLM fine-tuned to support contexts with more than 65K tokens
nateraw/nous-hermes-llama2-awq
TheBloke/Nous-Hermes-Llama2-AWQ served with vLLM
![](https://tjzk.replicate.delivery/models_models_cover_image/84f4d8b1-791c-4ea8-a380-a9c4aa8bc64e/replicate-prediction-z5kvthdbfone.png)
joehoover/zephyr-7b-alpha
A high-performing language model trained to act as a helpful assistant
![](https://tjzk.replicate.delivery/models_models_cover_image/f1e31126-4ba2-441e-a62f-80f492b5d403/gemma.jpg)
google-deepmind/gemma-7b
7B base version of Google’s Gemma model
hikikomori-haven/solar-uncensored
![](https://tjzk.replicate.delivery/models_models_cover_image/648fce8c-5ec5-48dd-bb40-4d6f0030a77a/large-1.png)
meta/codellama-34b-python
A 34 billion parameter Llama tuned for coding with Python
![](https://tjzk.replicate.delivery/models_models_featured_image/a11a4c0d-8f51-447f-b8e1-7b0af921bbe8/replicate-prediction-apk97rpxg.png)
cuuupid/glm-4v-9b
GLM-4V is a multimodal model released by Tsinghua University that is competitive with GPT-4o and establishes a new SOTA on several benchmarks, including OCR.
![](https://tjzk.replicate.delivery/models_models_cover_image/fb278ba6-f69a-481f-ae1f-8c286d868853/zephyr-replicate.png)
nateraw/zephyr-7b-beta
Zephyr-7B-beta, an LLM trained to act as a helpful assistant.
![](https://tjzk.replicate.delivery/models_models_featured_image/50fb361f-920e-46bf-af7f-057c72f645a4/llama-skate.png)
replicate/llama-13b-lora
Transformers implementation of the LLaMA 13B language model
![](https://replicate.delivery/pbxt/Kq17Ws2RLIXdeFeep2N56psrMVq57TPssPrffeF8HawmOhvD/frieren.jpg)
lucataco/llama-3-vision-alpha
Projection module trained to add vision capabilties to Llama 3 using SigLIP
![](https://tjzk.replicate.delivery/models_models_cover_image/3d482cbd-3da2-474f-8347-5d2621e6d85b/replicate-prediction-enqaaudbhjo5.png)
nomagick/qwen-14b-chat
Qwen-14B-Chat is a Transformer-based large language model, which is pretrained on a large volume of data, including web texts, books, codes, etc.
![](https://tjzk.replicate.delivery/models_models_cover_image/c31bd5f8-364b-4388-be72-4434d661d9b7/microsoft.webp)
lucataco/phi-3-mini-128k-instruct
Phi-3-Mini-128K-Instruct is a 3.8 billion-parameter, lightweight, state-of-the-art open model trained using the Phi-3 datasets
![](https://tjzk.replicate.delivery/models_models_cover_image/ac41dca3-992b-456b-9ff1-4b4b53d30b17/ldkN1J0WIDQwU4vutGYiD.png)
mikeei/dolphin-2.9-llama3-70b-gguf
Dolphin is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant.
![](https://tjzk.replicate.delivery/models_models_cover_image/d1e14d9c-023a-4fb3-aee7-b4ad2c621655/dolphin_2_7_mixtral.png)
kcaverly/dolphin-2.7-mixtral-8x7b-gguf
Uncensored Mixtral-8x7b MOE model trained for chat with the Dolphin dataset
![](https://tjzk.replicate.delivery/models_models_cover_image/30bfbd81-5028-4553-be44-dc063ccae993/yi_thumbnail.png)
01-ai/yi-6b-chat
The Yi series models are large language models trained from scratch by developers at 01.AI.
![](https://tjzk.replicate.delivery/models_models_cover_image/4d60d24d-fc0c-42ac-8ea7-a678a456d50b/salmonn_icon.png)
nateraw/salmonn
SALMONN: Speech Audio Language Music Open Neural Network
![](https://tjzk.replicate.delivery/models_models_cover_image/df6f6ad1-f867-4f84-a0b7-438ae744cd43/medium-5.png)
meta/codellama-13b-python
A 13 billion parameter Llama tuned for coding with Python
![](https://tjzk.replicate.delivery/models_models_cover_image/1b725996-846c-47cc-af38-90c7fc6568f1/qwen.webp)
lucataco/qwen1.5-72b
Qwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data
![](https://tjzk.replicate.delivery/models_models_cover_image/5cee6b49-1f78-447a-97cd-121feb18cbb0/small-4.png)
meta/codellama-7b-python
A 7 billion parameter Llama tuned for coding with Python
joehoover/sql-generator
![](https://replicate.delivery/pbxt/K8TFs6lkP6mT8vo8gk8e4eRKmwwGGv9gTDspwF0LTE3LHjKQ/zucker-scultpure.png)
anotherjesse/llava-lies
LLaVA injecting randomness into the image
![](https://tjzk.replicate.delivery/models_models_cover_image/0b762f45-eef5-470b-82f0-d76d1e2e34e9/dolphin_2_6.png)
kcaverly/dolphin-2.6-mixtral-8x7b-gguf
Mixtral-8x7b MOE model trained for chat with the dolphin + samantha's empathy dataset
![](https://tjzk.replicate.delivery/models_models_cover_image/34d81ffd-7d30-4274-a677-f5f114081e3f/qwen.webp)
lucataco/qwen1.5-110b
Qwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data
organisciak/ocsai-llama2-7b
![](https://tjzk.replicate.delivery/models_models_featured_image/392a2cf7-2067-4f8c-94e2-4ba2f909d02e/yi_thumbnail.png)
01-ai/yi-34b
The Yi series models are large language models trained from scratch by developers at 01.AI.
![](https://tjzk.replicate.delivery/models_models_cover_image/da752e69-0dff-4a04-8a02-0f238bbeda1e/kcaverly_robot_coding_with_ai_--v.png)
kcaverly/deepseek-coder-33b-instruct-gguf
A quantized 33B parameter language model from Deepseek for SOTA repository level code completion
![](https://tjzk.replicate.delivery/models_models_cover_image/008e8ee0-232c-4710-82c9-d69590d1fe3d/replicate-prediction-nb6c4m3bgvmt.png)
andreasjansson/llama-2-70b-chat-gguf
Llama-2 70B chat with support for grammars and jsonschema
![](https://tjzk.replicate.delivery/models_models_cover_image/e53394a6-d610-4192-b267-993bb9997c3c/Screenshot_2024-02-12_at_14.52.10.png)
deepseek-ai/deepseek-math-7b-base
Pushing the Limits of Mathematical Reasoning in Open Language Models - Base model
![](https://tjzk.replicate.delivery/models_models_cover_image/a56da6ac-1bac-4722-8cc2-69c605e90a6a/replit.png)
replit/replit-code-v1-3b
Generate code with Replit's replit-code-v1-3b large language model
![](https://tjzk.replicate.delivery/models_models_featured_image/3e967884-9354-4088-9d4d-0b86bc05e72e/HQnQmNM1L3KXGhp0wUzHH.webp)
nousresearch/hermes-2-theta-llama-8b
Hermes-2 Θ (Theta) is the first experimental merged model released by Nous Research, in collaboration with Charles Goddard at Arcee, the team behind MergeKit.
![](https://tjzk.replicate.delivery/models_models_cover_image/9ef61486-9908-4608-8153-5fce0e29f9b9/yi_thumbnail.png)
01-ai/yi-34b-200k
The Yi series models are large language models trained from scratch by developers at 01.AI.
![](https://tjzk.replicate.delivery/models_models_cover_image/0e63e25f-60a1-470d-8c93-7a4bfe586e11/deepseek.png)
lucataco/deepseek-vl-7b-base
DeepSeek-VL: An open-source Vision-Language Model designed for real-world vision and language understanding applications
mattt/orca-2-13b
![](https://tjzk.replicate.delivery/models_models_cover_image/00da63a7-1bd5-477c-a790-0d5c3699996f/orca.png)
niron1/openorca-platypus2-13b
OpenOrca-Platypus2-13B is a merge of garage-bAInd/Platypus2-13B and Open-Orca/OpenOrcaxOpenChat-Preview2-13B.
![](https://tjzk.replicate.delivery/models_models_cover_image/027825ef-db51-4caf-993b-7ef5c77d9867/flan.png)
daanelson/flan-t5-large
A language model for tasks like classification, summarization, and more.
![](https://tjzk.replicate.delivery/models_models_cover_image/aa064ff0-b1f3-456e-a02d-f811ea437424/replicate-prediction-2nt2reh71hrg.png)
zsxkib/qwen2-7b-instruct
Qwen 2: A 7 billion parameter language model from Alibaba Cloud, fine tuned for chat completions
![](https://tjzk.replicate.delivery/models_models_cover_image/867eb166-89ca-49f4-a20a-c4d6b788183b/Screenshot_2024-02-12_at_14.52.10.png)
deepseek-ai/deepseek-math-7b-instruct
Pushing the Limits of Mathematical Reasoning in Open Language Models - Instruct model
![](https://tjzk.replicate.delivery/models_models_cover_image/db02e422-63df-4644-8e7e-ee9bf30939b2/k-Rbd6RjQQK88i2G-SjDIg.png)
camenduru/wizardlm-2-8x22b
WizardLM 2 8x22B
![](https://tjzk.replicate.delivery/models_models_cover_image/b5f19a26-affd-4868-abed-c61af57be64b/oADz1HmUOOo9KNf0sfeSGKaxVrxPnHVh8.png)
meta/codellama-70b
A 70 billion parameter Llama tuned for coding and conversation
![](https://replicate.delivery/pbxt/GaxoRfU77xXBGS4hZEFfYszIy5WOpHAzszZc5JyDUn4ndxsRA/0019.jpg)
anotherjesse/sdxl-recur
explore img2img zooming sdxl
hayooucom/vision-model
This is phi-3-vision model , cost by time ,have fun~
![](https://tjzk.replicate.delivery/models_models_cover_image/fcd92324-723a-4823-9410-c4b4ad38ad29/bz7KMO6eZd0Oa6s2FNlReOcDIude3ZGoG.png)
meta/codellama-70b-python
A 70 billion parameter Llama tuned for coding with Python
![](https://tjzk.replicate.delivery/models_models_cover_image/1c5aff01-82a1-45e2-8864-ab59647e691e/jack.png)
niron1/qwen-7b-chat
Qwen-7B is the 7B-parameter version of the large language model series, Qwen (abbr. Tongyi Qianwen), proposed by Aibaba Cloud. Qwen-7B`is a Transformer-based large language model, which is pretrained on a large volume of data, including web texts, books,
![](https://tjzk.replicate.delivery/models_models_cover_image/d5ae7d4b-389a-4b03-9d45-1df07bf052b2/squared_image_padded.png)
nateraw/causallm-14b
CausalLM/14B model with AWQ quantization. Perhaps better than all existing models < 70B, in most quantitative evaluations...
![](https://tjzk.replicate.delivery/models_models_cover_image/aee46746-142d-48f1-b655-a2fbd1aa28d1/capybara_34b.png)
kcaverly/nous-capybara-34b-gguf
A SOTA Nous Research finetune of 200k Yi-34B fine tuned on the Capybara dataset.
![](https://tjzk.replicate.delivery/models_models_cover_image/f8c22a28-cb74-435c-9afa-c1e6b04c24e2/Screenshot_2024-06-27_at_5.28.28P.png)
lucataco/gemma2-27b-it
Google's Gemma2 27b instruct model
nateraw/samsum-llama-2-13b
![](https://tjzk.replicate.delivery/models_models_cover_image/0e693cea-d063-491e-98bd-4038f3fe8387/out-1-01.jpeg)
spuuntries/miqumaid-v2-2x70b-dpo-gguf
NeverSleep's MiquMaid v2 2x70B Miqu-Mixtral MoE DPO Finetune, GGUF Q2_K quantized by NeverSleep.
![](https://tjzk.replicate.delivery/models_models_cover_image/a75d9108-4dfc-4207-8850-fbd64be44875/llama-tools.png)
hamelsmu/llama-3-70b-instruct-awq-with-tools
Function calling with llama-3 with prompting only.
![](https://tjzk.replicate.delivery/models_models_cover_image/28082bf2-71b1-4d1a-a782-c768a0d8778c/replicate-prediction-5eouup3b67bn.png)
andreasjansson/codellama-34b-instruct-gguf
CodeLlama-34B-instruct with support for grammars and jsonschema
![](https://tjzk.replicate.delivery/models_models_cover_image/33841b6b-e21e-4746-9483-d38a9e4f54e6/replicate-prediction-dvht5blbrfyi.png)
nomagick/qwen-vl-chat
Qwen-VL-Chat but with raw ChatML prompt interface and streaming
nwhitehead/llama2-7b-chat-gptq
![](https://tjzk.replicate.delivery/models_models_cover_image/c9f08ec9-e198-41cf-b924-b0ee535c9d75/replicate-prediction-nb6c4m3bgvmt.png)
andreasjansson/wizardcoder-python-34b-v1-gguf
WizardCoder-python-34B-v1.0 with support for grammars and jsonschema
![](https://tjzk.replicate.delivery/models_models_cover_image/1aaf8cb7-cfaa-4a54-a9d6-6aecce05de1d/replicate-prediction-nb6c4m3bgvmt.png)
andreasjansson/llama-2-13b-gguf
Llama-2 13B with support for grammars and jsonschema
moinnadeem/vllm-engine-llama-7b
charles-dyfis-net/llama-2-13b-hf--lmtp-8bit
![](https://tjzk.replicate.delivery/models_models_cover_image/88707a3e-6230-4065-86ea-64e21a59bb50/qwen2.png)
lucataco/qwen2-57b-a14b-instruct
Qwen2 57 billion parameter language model from Alibaba Cloud, fine tuned for chat completions
ruben-svensson/llama2-aqua-test1
![](https://tjzk.replicate.delivery/models_models_cover_image/2ecc3f85-ba02-433c-b0e5-c72ab1d88fbf/gemma.jpg)
google-deepmind/gemma-2b
2B base version of Google’s Gemma model
antoinelyset/openhermes-2.5-mistral-7b-awq
papermoose/llama-pajama
![](https://tjzk.replicate.delivery/models_models_featured_image/b42b6ff0-043b-4acf-96b7-6f474fb9e434/stablelm-7b.png)
stability-ai/stablelm-base-alpha-7b
7B parameter base version of Stability AI's language model
![](https://tjzk.replicate.delivery/models_models_cover_image/17b46ced-7a2d-4465-bcb9-c172f9d29373/fofr_a_llama_using_a_paintbrush_t.png)
fofr/llama2-prompter
Llama2 13b base model fine-tuned on text to image prompts
![](https://tjzk.replicate.delivery/models_models_cover_image/2417ab67-af9f-412e-bdf8-1e5da834a368/ldkN1J0WIDQwU4vutGYiD.png)
mikeei/dolphin-2.9-llama3-8b-gguf
Dolphin is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant.
![](https://tjzk.replicate.delivery/models_models_cover_image/9d138765-12ad-4eba-b2e1-1d11e70d2404/kcaverly_very_big_robot_coding_on.png)
kcaverly/deepseek-coder-6.7b-instruct
A ~7B parameter language model from Deepseek for SOTA repository level code completion
![](https://tjzk.replicate.delivery/models_models_cover_image/8af49357-708c-42b5-bea2-5816a0abcdd7/for_esteemed_human-02.jpg)
spuuntries/erosumika-7b-v3-0.2-gguf
localfultonextractor's Erosumika 7B Mistral Merge, GGUF Q4_K_S-imat quantized by Lewdiculous.
![](https://tjzk.replicate.delivery/models_models_cover_image/e4053988-4697-4a58-9e8d-661ec6044d8e/hermes2pro.png)
lucataco/hermes-2-pro-llama-3-8b
Hermes 2 Pro is an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house
nateraw/sqlcoder-70b-alpha
![](https://tjzk.replicate.delivery/models_models_cover_image/ba5b0387-5b6c-4a5e-9ffe-a6f7acaa761e/fofr_a_star_trek_officer_reading_.png)
fofr/star-trek-gpt-j-6b
gpt-j-6b trained on the Memory Alpha Star Trek Wiki
replicate-internal/staging-llama-2-7b
![](https://tjzk.replicate.delivery/models_models_cover_image/00b8809c-1160-49ce-b061-656c33910c88/Screenshot_2024-06-27_at_5.28.28P.png)
lucataco/gemma2-9b-it
Google's Gemma2 9b instruct model
![](https://tjzk.replicate.delivery/models_models_featured_image/e87b4595-9e49-4be2-b267-dae664522b92/stablelm-3b.png)
stability-ai/stablelm-base-alpha-3b
3B parameter base version of Stability AI's language model
![](https://tjzk.replicate.delivery/models_models_cover_image/3b41e5dd-c57b-426b-b497-db14085e8421/cap.gif)
andreasjansson/plasma
Generate plasma shader equations
![](https://tjzk.replicate.delivery/models_models_cover_image/78245ea5-1db6-43ad-96f8-8bb8e863e67b/6kiCWL4hSaeSqLxfX3rjyQ.png)
camenduru/mixtral-8x22b-instruct-v0.1
Mixtral 8x22b Instruct v0.1
theghoul21/srl
![](https://tjzk.replicate.delivery/models_models_cover_image/f6596640-cfa3-4b13-935d-3a06b3943855/dolphin_2.6_mistral.png)
kcaverly/dolphin-2.6-mistral-7b-gguf
Mistral 7b v2 Fine Tuned on the Dolphin dataset
![](https://tjzk.replicate.delivery/models_models_cover_image/688ff712-1d7c-478a-9426-56bb6248afff/tinyllama.webp)
lucataco/tinyllama-1.1b-chat-v1.0
This is the chat model finetuned on top of TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
![](https://tjzk.replicate.delivery/models_models_cover_image/09b6cb10-8543-4bc2-bfc4-bd21a49e53c2/replicate-prediction-ctmgindbbbr6.png)
nomagick/chatglm3-6b-32k
A 6B parameter open bilingual chat LLM (optimized for 8k+ context) | 开源双语对话语言模型
![](https://tjzk.replicate.delivery/models_models_cover_image/df71f090-9bfd-4894-8506-44a3adbbeead/english_to_hinglish_thumbnail.png)
nateraw/axolotl-llama-2-7b-english-to-hinglish
![](https://replicate.delivery/pbxt/KSjaaQ4oatw4iARoNoU7orjhXpwB9m2LlOd4ifpe1gqZXWIo/img3.12.jpg)
ignaciosgithub/pllava
![](https://tjzk.replicate.delivery/models_models_cover_image/ed04609c-5f64-4b27-9dd2-dccad8da7256/qwen.webp)
lucataco/qwen1.5-14b
Qwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data
![](https://tjzk.replicate.delivery/models_models_cover_image/e65c57eb-8afe-42ce-b089-e65be5215c58/lemma-logo.png)
peter65374/openbuddy-llemma-34b-gguf
This is a cog implementation of "openbuddy-llemma-34b" 4-bit quantization model.
![](https://tjzk.replicate.delivery/models_models_cover_image/75988acf-bfb0-4684-aa36-377166e05b76/llama3.png)
niron1/llama-2-7b-chat
LLAMA-2 7b chat version by Meta. Stream support. Unaltered prompt. Temperature working properly. Economical hardware.
cbh123/dylan-lyrics
Llama 2 13B fine-tuned on Bob Dylan lyrics
antoinelyset/openhermes-2-mistral-7b
Simple version of https://huggingface.co/teknium/OpenHermes-2-Mistral-7B
![](https://tjzk.replicate.delivery/models_models_cover_image/34454af1-6ec7-40d0-86dc-ee3e8cc016a5/iSdkSIYLTGun57PkOBuFkA.png)
camenduru/mixtral-8x22b-v0.1-instruct-oh
Mixtral-8x22b-v0.1-Instruct-Open-Hermes
![](https://tjzk.replicate.delivery/models_models_cover_image/276d4584-e364-41bd-82b2-34b44e471c89/kcaverly_phind_coding_llama_--ar_.png)
kcaverly/phind-codellama-34b-v2-gguf
A quantized 34B parameter language model from Phind for code completion
![](https://tjzk.replicate.delivery/models_models_cover_image/c46544ab-db95-429b-a131-2b5c811d3184/out-1_3.png)
adirik/mamba-2.8b
Base version of Mamba 2.8B, a 2.8 billion parameter state space language model
hayooucom/llm-60k
llm model ,for CN
![](https://tjzk.replicate.delivery/models_models_cover_image/ca04cf6a-f6d1-4bf0-b07b-c68fa3d55bfe/kqm9ddydl8_1689082483825.png)
nomagick/chatglm2-6b-int4
ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型 (int4)
![](https://tjzk.replicate.delivery/models_models_cover_image/3c2d374c-5674-44fd-88fc-192e370fbe78/UOb2fvh.jpg)
lucataco/phixtral-2x2_8
phixtral-2x2_8 is the first Mixure of Experts (MoE) made with two microsoft/phi-2 models, inspired by the mistralai/Mixtral-8x7B-v0.1 architecture
![](https://tjzk.replicate.delivery/models_models_cover_image/a8c4bc0c-1f1f-49fe-bf3f-c58e58e5708a/ldkN1J0WIDQwU4vutGYiD.png)
mikeei/dolphin-2.9.1-llama3-8b-gguf
Dolphin is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant.
zeke/nyu-llama-2-7b-chat-training-test
A test model for fine-tuning Llama 2
![](https://tjzk.replicate.delivery/models_models_cover_image/ac0ddf95-5ace-490d-912f-9bf320118f55/hermes_solar.png)
kcaverly/nous-hermes-2-solar-10.7b-gguf
Nous Hermes 2 - SOLAR 10.7B is the flagship Nous Research model on the SOLAR 10.7B base model.
![](https://tjzk.replicate.delivery/models_models_cover_image/30768c9f-8d07-4e99-92f2-0f5a91b2e878/deepseek.png)
lucataco/deepseek-coder-v2-lite-instruct
DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence
![](https://tjzk.replicate.delivery/models_models_cover_image/7815682b-4c47-42fc-8d43-1f72bf443346/hc2.png)
hamelsmu/honeycomb-2
Honeycomb NLQ Generator
![](https://tjzk.replicate.delivery/models_models_cover_image/10f332ea-fa83-4953-b77a-28e390933f0e/3fccd7_2575ab25603e414f98ba48e856.jpg)
xrunda/med
![](https://tjzk.replicate.delivery/models_models_cover_image/c312f16d-5c24-43c1-9c26-52a2a8188e01/replicate-prediction-2nt2reh71hrg.png)
zsxkib/qwen2-1.5b-instruct
Qwen 2: A 1.5 billion parameter language model from Alibaba Cloud, fine tuned for chat completions
![](https://tjzk.replicate.delivery/models_models_cover_image/5cb9fa5b-3b37-4bfb-b9a3-58ebe016836e/robotic_raven.png)
kcaverly/nexus-raven-v2-13b-gguf
A quantized 13B parameter language model from NexusFlow for SOTA zero-shot function calling
zallesov/super-real-llama2
fofr/star-trek-adventure
![](https://tjzk.replicate.delivery/models_models_cover_image/f56d789a-1bfc-456c-a4cd-42643cc3ee45/replicate-prediction-2nt2reh71hrg.png)
zsxkib/qwen2-0.5b-instruct
Qwen 2: A 0.5 billion parameter language model from Alibaba Cloud, fine tuned for chat completions
nateraw/stablecode-completion-alpha-3b-4k
![](https://tjzk.replicate.delivery/models_models_cover_image/c6042d90-4de0-47bd-916f-4342907bbef8/hermes-2-theta.png)
lucataco/hermes-2-theta-llama-3-70b
Hermes-2 Θ (Theta) 70B is the continuation of our experimental merged model released by Nous Research
![](https://tjzk.replicate.delivery/models_models_cover_image/3dfdade4-b042-4439-85df-a2fbacf54c47/ollama.png)
lucataco/ollama-deepseek-coder-v2-236b
Cog wrapper for Ollama deepseek-coder-v2:236b
![](https://tjzk.replicate.delivery/models_models_cover_image/22baba54-eb23-422e-a9b3-fb18ea35bb66/neuromancer-llama_1.png)
fofr/neuromancer-13b
llama-13b-base fine-tuned on Neuromancer style
![](https://tjzk.replicate.delivery/models_models_cover_image/80592e5f-7f61-4be0-a321-1315cbefcb50/_0af58730-bfca-4fb6-8989-2ee92da.jpeg)
swartype/lanne-m1-70b
Lanne M1 is the first language model produced by Lanne Tech. It is based on +70B of parameters. With performance equivalent to GPT3.5.
m1guelpf/mario-gpt
Using language models to generate Super Mario Bros levels
![](https://tjzk.replicate.delivery/models_models_cover_image/dc34fa6b-cb23-40ab-99da-2d8cba933507/4aF1JALUS6-GvZoe2k4swQ.png)
camenduru/zephyr-orpo-141b-a35b-v0.1
Mixtral 8x22b v0.1 Zephyr Orpo 141b A35b v0.1
![](https://tjzk.replicate.delivery/models_models_cover_image/c8a6f7fd-2166-4aff-a766-9f9d8169a097/typewriter2.png)
nateraw/samsum-llama-7b
llama-2-7b fine-tuned on the samsum dataset for dialogue summarization
![](https://tjzk.replicate.delivery/models_models_cover_image/9c352605-560b-422d-a077-362534ff4817/B7CA2030-278B-49CD-94D5-4DD142C73.png)
fofr/star-trek-flan
flan-t5-xl trained on the Memory Alpha Star Trek Wiki
![](https://tjzk.replicate.delivery/models_models_featured_image/74e4fa69-beb2-4b92-a347-8fcd8516d7d1/minicpm-llama3-v-2.5.png)
cuuupid/minicpm-llama3-v-2.5
MiniCPM LLama3-V 2.5, a new SOTA open-source VLM that surpasses GPT-4V-1106 and Phi-128k on a number of benchmarks.
![](https://tjzk.replicate.delivery/models_models_cover_image/55d0a366-2c7e-46a1-a83a-334f088e55cd/fofr_llama_in_starfleet_uniform_8.png)
fofr/star-trek-llama
llama-7b trained on the Memory Alpha Star Trek Wiki
![](https://tjzk.replicate.delivery/models_models_cover_image/86e09ef7-ca5e-4479-9714-59b6fb8bedbe/argilla.png)
titocosta/notus-7b-v1
Notus-7b-v1 model
moinnadeem/fastervicuna_13b
Re-implements LLaMa using a higher MFU implementation
![](https://tjzk.replicate.delivery/models_models_cover_image/e6699590-1255-4fbd-ae01-309dff015930/qwen.webp)
lucataco/qwen1.5-7b
Qwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data
nateraw/llama-2-7b-paraphrase-v1
cbh123/samsum
![](https://tjzk.replicate.delivery/models_models_cover_image/8d336548-0146-460e-a250-c2e3ae2980bb/out-1_3.png)
adirik/mamba-130m
Base version of Mamba 130M, a 130 million parameter state space language model
cjwbw/opencodeinterpreter-ds-6.7b
OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement
![](https://tjzk.replicate.delivery/models_models_cover_image/408eb2f4-19b1-4ecd-beb8-9f866981bc3c/hermes2pro.png)
lucataco/hermes-2-pro-llama-3-70b
Hermes 2 Pro is an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house
![](https://tjzk.replicate.delivery/models_models_cover_image/c2327901-06f0-4a2e-a476-d16bcf9a6be5/110470554.png)
cjwbw/starcoder2-15b
Language Models for Code
rybens92/una-cybertron-7b-v2--lmtp-8bit
nateraw/wizardcoder-python-34b-v1.0
automorphic-ai/runhouse
![](https://tjzk.replicate.delivery/models_models_cover_image/630915ee-2a63-432a-a9ae-8b315e81f3ac/NKM5xD5q_400x400.jpg)
crowdy/line-lang-3.6b
an implementation of 3.6b Japanese large language model
nateraw/llama-2-7b-chat-hf
nateraw/aidc-ai-business-marcoroni-13b
moinnadeem/codellama-34b-instruct-vllm
tanzir11/merge
![](https://tjzk.replicate.delivery/models_models_cover_image/b2df520a-fda9-43b9-a792-55f4ccb3a79e/ai2.webp)
lucataco/olmo-7b
OLMo is a series of Open Language Models designed to enable the science of language models
![](https://tjzk.replicate.delivery/models_models_cover_image/9151b94e-dd23-4125-bda5-e46d1759b04c/y5SEKiE8TkjBKs9xfjCx5.webp)
lucataco/qwen1.5-1.8b
Qwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data
![](https://tjzk.replicate.delivery/models_models_cover_image/1a0bc0dd-304a-4284-8246-2e4754c56fa0/out-0_16.png)
spuuntries/borealis-10.7b-dpo-gguf
Undi95's Borealis 10.7B Mistral DPO Finetune, GGUF Q5_K_M quantized by Undi95.
nateraw/codellama-7b-instruct-hf
![](https://tjzk.replicate.delivery/models_models_cover_image/32038c6f-71b8-416f-8f47-d6649b8526c7/abby_5.jpg)
juanjaragavi/abby-llama-2-7b-chat
Abby is a stoic philosopher and a loving and caring mature woman.
![](https://tjzk.replicate.delivery/models_models_cover_image/1b5b83ed-fba7-44b4-bee6-3ceb0de307eb/WX20231027-1704082x.png)
peter65374/openbuddy-mistral-7b
Openbuddy finetuned mistral-7b in GPTQ quantization in 4bits by TheBloke
![](https://tjzk.replicate.delivery/models_models_cover_image/699aacbc-9166-4eff-923a-cc6bbc55f0c9/6863069c-a667-4b01-b472-19d4247d.webp)
lidarbtc/kollava-v1.5
korean version of llava-v1.5
![](https://tjzk.replicate.delivery/models_models_cover_image/660d5f70-54d0-468e-b073-d879821038be/noushermes2.jpg)
lucataco/nous-hermes-2-mixtral-8x7b-dpo
Nous Hermes 2 Mixtral 8x7B DPO is a Nous Research model trained over the Mixtral 8x7B MoE LLM
replicate-internal/mixtral-8x7b-instruct-v0.1-pget
![](https://replicate.delivery/pbxt/KZekorriicHO6YRgz0GH7pIhZs5lGGHe9sJgGMD71ItSTctT/image.jpeg)
martintmv-git/moondream2
small vision language model
![](https://tjzk.replicate.delivery/models_models_cover_image/0f37a80b-576f-4449-be14-8ec07ef5dbb1/y5SEKiE8TkjBKs9xfjCx5.webp)
lucataco/qwen1.5-0.5b
Qwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data
![](https://tjzk.replicate.delivery/models_models_cover_image/e7ce877e-f66d-4d45-a90f-e66d8ce2f56b/qwen2.png)
lucataco/qwen2-72b-instruct
Qwen 2: A 72 billion parameter language model fine tuned for chat completions
![](https://replicate.delivery/pbxt/Jv7hB84kxm3TKjmhS2g8NCFaqhaT5FRChkzV7Sehq5Psk9Ob/3.jpg)
chigozienri/llava-birds
![](https://tjzk.replicate.delivery/models_models_cover_image/8913e804-0e44-455d-9153-4b7dbbe115ef/yi-logo.jpg)
lucataco/yi-1.5-6b
Yi-1.5 is continuously pre-trained on Yi with a high-quality corpus of 500B tokens and fine-tuned on 3M diverse fine-tuning samples
dsingal0/mixtral-single-gpu
Runs Mixtral 8x7B on a single A40 GPU
![](https://tjzk.replicate.delivery/models_models_cover_image/7359069d-973b-45b2-9a67-4a20f823c53b/PavisyFb_400x400.png)
cjwbw/c4ai-command-r-v01
CohereForAI c4ai-command-r-v01, Quantized model through bitsandbytes, 8-bit precision
![](https://tjzk.replicate.delivery/models_models_cover_image/82ea9cfb-95bf-48b6-8b06-9e5a9a2e27e1/out-1_3.png)
adirik/mamba-1.4b
Base version of Mamba 1.4B, a 1.4 billion parameter state space language model
![](https://tjzk.replicate.delivery/models_models_cover_image/4973f105-c7ab-435b-8c7c-0dde92cc6349/out-1_3.png)
adirik/mamba-2.8b-slimpj
Base version of Mamba 2.8B Slim Pyjama, a 2.8 billion parameter state space language model
cbh123/homerbot
![](https://tjzk.replicate.delivery/models_models_cover_image/ef78b2cf-5df1-4afc-9ac7-1f62a5c6fa3b/deepseek.png)
lucataco/deepseek-67b-base
DeepSeek LLM, an advanced language model comprising 67 billion parameters. Trained from scratch on a vast dataset of 2 trillion tokens in both English and Chinese
![](https://tjzk.replicate.delivery/models_models_cover_image/82443f27-703d-4eae-bd39-133795336f31/hc-fast.png)
replicate-internal/staging-honeycomb-triton
A fast version of replicate.com/hamelsmu/honeycomb-2 using TRT-LLM
![](https://tjzk.replicate.delivery/models_models_cover_image/d784ffaf-2aef-4fe9-b268-59d84daee1fa/starling.png)
titocosta/starling
Starling-LM-7B-alpha
replicate/elixir-gen
Fine-tuned Llama 13b on Elixir docstrings (WIP)
technillogue/mixtral-instruct-nix
![](https://tjzk.replicate.delivery/models_models_cover_image/bb41e380-ac7a-41df-96a9-6030cfb46eb7/out-1_3.png)
adirik/mamba-370m
Base version of Mamba 370M, a 370 million parameter state space language model
nateraw/llama-2-7b-samsum
![](https://tjzk.replicate.delivery/models_models_cover_image/97242c08-cfff-43c1-8d34-80a627770df4/hc_replicate_cover.png)
hamelsmu/honeycomb
Honeycomb NLQ Generator
![](https://tjzk.replicate.delivery/models_models_cover_image/bbec284b-b3cb-43dc-8bc7-0908b07288a5/out-1_3.png)
adirik/mamba-790m
Base version of Mamba 790M, a 790 million parameter state space language model
sruthiselvaraj/finetuned-llama2
![](https://tjzk.replicate.delivery/models_models_cover_image/324bf209-9d74-4b75-a591-91acc3d0946f/replicate-prediction-xshmr0vs7srg.png)
lorenzomarines/nucleum-theta-240
A powerful LLM competitive with Claude Sonnet and GPT 3.5 but fully opensource and Decentralized
![](https://tjzk.replicate.delivery/models_models_cover_image/8025835a-3137-46f9-9f8b-57b8f78c5da8/qwen.webp)
lucataco/qwen1.5-32b
Qwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data
nateraw/gairmath-abel-7b
![](https://tjzk.replicate.delivery/models_models_cover_image/7de5151d-c5a0-4c19-b43a-3f5c72aff90e/internlm-logo.webp)
lucataco/internlm2_5-7b-chat
InternLM2.5 has open-sourced a 7 billion parameter base model and a chat model tailored for practical scenarios.
lorenzomarines/nucleum-apollonio-14b
seanoliver/bob-dylan-fun-tuning
Llama fine-tune-athon project training llama2 on bob dylan lyrics.
intentface/poro-34b-gguf-checkpoint
Try out akx/Poro-34B-gguf, Q5_K, This is 1000B checkpoint model
fleshgordo/orni2-chat
![](https://tjzk.replicate.delivery/models_models_cover_image/b35373a9-b954-4b5d-970e-e2dd9d0c24ef/qwen.webp)
lucataco/qwen1.5-4b
Qwen1.5 is the beta version of Qwen2, a transformer-based decoder-only language model pretrained on a large amount of data
![](https://tjzk.replicate.delivery/models_models_cover_image/a2297d00-13bd-48e9-bbfd-2371b3e38cef/dolphin-2.9.png)
lucataco/dolphin-2.9-llama3-8b
Dolphin-2.9 has a variety of instruction, conversational, and coding skills. It also has initial agentic abilities and supports function calling
nateraw/codellama-7b-instruct
mattt/whisper-tiny-en
charles-dyfis-net/llama-2-7b-hf--lmtp-4bit
nateraw/codellama-34b
johnnyoshika/llama2-combine-numbers
divyavanmahajan/my-pet-llama
![](https://tjzk.replicate.delivery/models_models_cover_image/66d1950b-4caa-4219-965a-b2718eb03b02/abbot_6.jpg)
juanjaragavi/abbot-llama-2-7b-chat
Abbot is brutally honest stoic philosopher. He is here to help the 'User' be their best self, no coddling.
msamogh/iiu-generator-llama2-7b-2
jquintanilla4/qwen1.5-32b-chat
Qwen1.5 32B Chat variant. A transformer-based decoder-only language model. Good with Chinese and English.
nateraw/codellama-7b
mattt/whisper-large-streaming
![](https://tjzk.replicate.delivery/models_models_cover_image/fad33837-0e9b-4177-baa2-ca96dea0fdcf/hermes-2-theta.png)
lucataco/hermes-2-theta-llama-3-8b
Hermes-2 Θ (Theta) is the first experimental merged model released by Nous Research
charles-dyfis-net/llama-2-13b-hf--lmtp
replicate-internal/gemma-2b-it
2B instruct version of the Gemma model
halevi/sandbox1
hayooucom/vision-llama3
for test
![](https://tjzk.replicate.delivery/models_models_cover_image/e7da38bf-3be3-44d1-8e22-15e0b526e274/mistral.webp)
lucataco/mistral-7b-instruct-v0.3
The Mistral-7B-Instruct-v0.3 Large Language Model is an instruct fine-tuned version of the Mistral-7B-v0.3
![](https://tjzk.replicate.delivery/models_models_cover_image/4ae14bc8-8e79-43c3-a7ae-051bd4c114c6/numina.webp)
lucataco/numinamath-7b-tir
NuminaMath is a series of language models that are trained to solve math problems using tool-integrated reasoning (TIR)
nateraw/codellama-13b
demonpore-sys/llamaxine0.1
charles-dyfis-net/llama-2-13b-hf--lmtp-4bit
nateraw/codellama-13b-instruct
![](https://tjzk.replicate.delivery/models_models_cover_image/b4fff2fb-75d2-40fe-a663-b3a96a803aae/ollama.png)
lucataco/ollama-llama3-70b
Cog wrapper for Ollama llama3:70b
![](https://tjzk.replicate.delivery/models_models_cover_image/d4cd06da-abef-4e6e-a447-03bb60d1bee4/ollama.png)
lucataco/ollama-llama3-8b
Cog wrapper for Ollama llama3:8b
replicate-internal/hermes-2-theta-l3-8b-fp16-triton