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.
gpt2Qwen2.5-0.5B-InstructQwen2.5-7B-InstructLlama-3.2-1B-InstructQwen2.5-1.5B-Instructopt-125mLlama-3.1-8B-InstructQwen2.5-3B-Instructpythia-160mQwen2.5-7B-Instruct-AWQNVIDIA-Nemotron-3-Nano-4B-BF16JiRackUltra_1bOTel-2.0-LLM-31B-ITQwen2.5-Coder-7B-InstructQwen3.8-27B-Uncensored-GGUFdistilgpt2Qwen2.5-32B-InstructSmolLM2-135M-InstructSmolLM2-135MQwen2.5-14B-Instruct-AWQGLM-4.7-FlashLlama-3.2-3B-InstructQwen2.5-Coder-14B-InstructQwen2.5-14B-InstructQwen2.5-0.5BGLM-5.3pythia-70m-dedupedNVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4TinyLlama-1.1B-Chat-v1.0deepseek-v4-gguf