AI Model Catalogue

Open-source Qwen2-7B-Instruct model from qwen — available for download and self-hosting on Hugging Face.

tiny-random-OPTForCausalLM

peft-internal-testing

Open-source tiny-random-OPTForCausalLM model from peft-internal-testing — available for download and self-hosting on Hugging Face.

tiny-random-LlamaForCausalLM

trl-internal-testing

Open-source tiny-random-LlamaForCausalLM model from trl-internal-testing — available for download and self-hosting on Hugging Face.

gemma-2-2b

google

Open-source gemma-2-2b model from google — available for download and self-hosting on Hugging Face.

Qwen2.5-72B-Instruct-AWQ

Open-source Qwen2.5-72B-Instruct-AWQ model from qwen — available for download and self-hosting on Hugging Face.

DeepSeek-R1-0528-Qwen3-8B-MLX-4bit

lmstudio-community

Open-source DeepSeek-R1-0528-Qwen3-8B-MLX-4bit model from lmstudio-community — available for download and self-hosting on Hugging Face.

mistral-7b-v0.3-bnb-4bit

unsloth

Open-source mistral-7b-v0.3-bnb-4bit model from unsloth — available for download and self-hosting on Hugging Face.

GLM-4.7-Flash

unsloth

Open-source GLM-4.7-Flash model from unsloth — available for download and self-hosting on Hugging Face.

tiny-GptOssForCausalLM

trl-internal-testing

Open-source tiny-GptOssForCausalLM model from trl-internal-testing — available for download and self-hosting on Hugging Face.

Mistral-Small-24B-Instruct-2501-AWQ

stelterlab

Open-source Mistral-Small-24B-Instruct-2501-AWQ model from stelterlab — available for download and self-hosting on Hugging Face.

tiny-Qwen3ForCausalLM

trl-internal-testing

Open-source tiny-Qwen3ForCausalLM model from trl-internal-testing — available for download and self-hosting on Hugging Face.

DeepSeek-R1-Distill-Qwen-14B

deepseek-ai

Open-source DeepSeek-R1-Distill-Qwen-14B model from deepseek-ai — available for download and self-hosting on Hugging Face.

phi-4

microsoft

Open-source phi-4 model from microsoft — available for download and self-hosting on Hugging Face.

Qwen3.5-397B-A17B-NVFP4

nvidia

Open-source Qwen3.5-397B-A17B-NVFP4 model from nvidia — available for download and self-hosting on Hugging Face.

DeepSeek-Coder-V2-Lite-Instruct

deepseek-ai

Open-source DeepSeek-Coder-V2-Lite-Instruct model from deepseek-ai — available for download and self-hosting on Hugging Face.

textcodeinstruct

Qwen2.5-Math-1.5B

Open-source Qwen2.5-Math-1.5B model from qwen — available for download and self-hosting on Hugging Face.

Llama-3.3-70B-Instruct

meta-llama

Open-source Llama-3.3-70B-Instruct model from meta-llama — available for download and self-hosting on Hugging Face.

LLaMA-1B-dj-refine-150B

datajuicer

Open-source LLaMA-1B-dj-refine-150B model from datajuicer — available for download and self-hosting on Hugging Face.

Qwen2-0.5B

Open-source Qwen2-0.5B model from qwen — available for download and self-hosting on Hugging Face.

TinyLlama-1.1B-Chat-v0.3-GPTQ

thebloke

Open-source TinyLlama-1.1B-Chat-v0.3-GPTQ model from thebloke — available for download and self-hosting on Hugging Face.

Qwen2.5-72B-Instruct

Open-source Qwen2.5-72B-Instruct model from qwen — available for download and self-hosting on Hugging Face.

DeepSeek-V3-0324

deepseek-ai

Open-source DeepSeek-V3-0324 model from deepseek-ai — available for download and self-hosting on Hugging Face.

NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4

nvidia

Open-source NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4 model from nvidia — available for download and self-hosting on Hugging Face.

Qwen3-235B-A22B

Open-source Qwen3-235B-A22B model from qwen — available for download and self-hosting on Hugging Face.

textcheaplong-context

Qwen3-Coder-Next-8bit

nexveridian

Open-source Qwen3-Coder-Next-8bit model from nexveridian — available for download and self-hosting on Hugging Face.

textcodefree

Llama-2-7b-chat-hf

meta-llama

Open-source Llama-2-7b-chat-hf model from meta-llama — available for download and self-hosting on Hugging Face.

Mistral-7B-Instruct-v0.1

mistralai

Open-source Mistral-7B-Instruct-v0.1 model from mistralai — available for download and self-hosting on Hugging Face.

gemma-2-2b-it

google

Open-source gemma-2-2b-it model from google — available for download and self-hosting on Hugging Face.

xlnet-base-cased

xlnet

Open-source xlnet-base-cased model from xlnet — available for download and self-hosting on Hugging Face.

SmolLM2-360M-Instruct

huggingfacetb

Open-source SmolLM2-360M-Instruct model from huggingfacetb — available for download and self-hosting on Hugging Face.

Deepseek V3.2

DeepSeek R1 (Original)

Deepseek V3.1 Terminus

Llama 4 Maverick Instruct (17Bx128E) FP8

Llama 4 Maverick 17B 128E

Qwen3.5 397B A17b Fp8

Qwen3.5 397B A17b Fp8 — Alibaba's Qwen series language model with strong multilingual and coding capabilities.

textfreelong-context

📏262kcontext