AI Model Catalogue

Open-source Qwen3-8B-AWQ model from qwen — available for download and self-hosting on Hugging Face.

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

Open-source bloomz-560m model from bigscience — available for download and self-hosting on Hugging Face.

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

Open-source phi-2 model from microsoft — available for download and self-hosting on Hugging Face.

Open-source Meta-Llama-3-8B-Instruct model from meta-llama — available for download and self-hosting on Hugging Face.

Open-source SmolLM2-135M model from huggingfacetb — available for download and self-hosting on Hugging Face.

Open-source Phi-3-mini-4k-instruct-gptq-4bit model from kaitchup — available for download and self-hosting on Hugging Face.

Open-source NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 model from nvidia — available for download and self-hosting on Hugging Face.

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

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

Open-source GLM-5-FP8 model from zai-org — available for download and self-hosting on Hugging Face.

Open-source NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 model from nvidia — available for download and self-hosting on Hugging Face.

Open-source Qwen3-Embedding-8B model from qwen — available for download and self-hosting on Hugging Face.

Open-source Qwen3-4B-Thinking-2507 model from qwen — available for download and self-hosting on Hugging Face.

Open-source Qwen3-Embedding-4B model from qwen — available for download and self-hosting on Hugging Face.

Open-source DeepSeek-R1-Distill-Llama-8B model from deepseek-ai — available for download and self-hosting on Hugging Face.

Open-source pythia-160m model from eleutherai — available for download and self-hosting on Hugging Face.

Open-source distilgpt2 model from distilbert — available for download and self-hosting on Hugging Face.

Open-source gpt2-large model from openai-community — available for download and self-hosting on Hugging Face.

Open-source Meta-Llama-3-8B model from meta-llama — available for download and self-hosting on Hugging Face.

Open-source gpt-oss-120b model from openai — available for download and self-hosting on Hugging Face.

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

Open-source gpt-oss-20b model from openai — available for download and self-hosting on Hugging Face.

Open-source opt-125m model from facebook — available for download and self-hosting on Hugging Face.

Open-source Qwen3-4B-Instruct-2507 model from qwen — available for download and self-hosting on Hugging Face.

Open-source Qwen3-4B model from qwen — available for download and self-hosting on Hugging Face.

Open-source gpt2 model from openai-community — available for download and self-hosting on Hugging Face.

Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...

Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...