models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
llama3.1-typhoon2-8b-instruct-ggufR1pathak-TinyLlama_v1.1_float16_0.0-GGUFllama3.2-typhoon2-1b-instruct-gguftyphoon2-qwen2.5-7b-instruct-ggufllama3.2-typhoon2-3b-instruct-ggufgpt4chan_model_float16PREMOVE_llama3.3-70b_float16DeepSeek-R1-Distill-Qwen-32B-float16gpt-neox-float16Josiefied-Qwen2.5-0.5B-Instruct-abliterated-v1-float16llama3.2-typhoon2-3b-instruct-mlx-6bitdipg-safety-agent-v2-float16llama3.2-typhoon2-1b-instruct-mlx-8bitllama3.2-typhoon2-3b-instruct-mlx-8bitqwen-8b-finetune-arg-v01-vllm-float16zh-tw-llm-ta01-pythia-70m-ta8000-v1-a_2_lora_instruction_tune-a100-t002-7a793a-merged-float16musang-mistral-7b-v3-float16-awqgranite-3b-code-instruct-128k-onnx-float16DeepSeek-R1-Medical-COT-float16gemma3-1b-sft-sitcom-office-reasoning-float16zh-tw-llm-ta01-pythia-70m-ta8000-v1-a_1_embeddings-a100-t4-ce784e-float16llama2-kv-sharing-float16llama3.1-typhoon2-8b-instruct-mlx-6bittyphoon2-qwen2.5-7b-instruct-mlx-4bitqwen3-4b-finetune-arg-v01-vllm-float16qwen-8b-finetune-dave-v03-vllm-float16llama_1b_merged_float16stablelm-3b-4e1t-onnx-float16calm2-7b-chat-dpo-experimental-float16Meta-Llama-3-8B-Instruct-ct2-int8_float16