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.
gpt2gpt2-largegpt-neox-20bQwen2.5-32B-Instruct-GPTQ-Int4Qwen2.5-Coder-7B-Instruct-GPTQ-Int4gpt2-mediumQwen2.5-14B-Instruct-GPTQ-Int4medgemma-27b-text-it-GPTQgpt2-minigpt2-xlQwen2.5-7B-Instruct-GPTQ-Int4Qwen3.8-27B-EfficientThink-Uncensored-K3-Opus5-Grok4.6-GPT5.6Sol-SFT-SimPO-DFlash2OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-ggufQwen3.8-27B-GPTQ-Int4-sym-G128-MTP-BF16OpenAi-GPT-oss-20b-HERETIC-uncensored-NEO-Imatrix-ggufSmolLM2-135M-Instruct-GPTQgpt-oss-20b-OptiQ-4bitQwen2.5-Coder-14B-Instruct-GPTQ-Int4gpt-neo-2.7Bmegatron-gpt2-345mQwen2.5-72B-Instruct-GPTQ-Int4GPT-OSS-Cybersecurity-20B-Merged-i1-GGUFLlama-2-7B-Chat-GPTQQwen2.5-3B-Instruct-GPTQ-Int4Qwen2-1.5B-Instruct-GPTQ-Int4GPT-X2-125M-CIx-Long-ContextMiniCPM5-2B-GPTQLlama-2-7B-GPTQGPT-OSS-Cybersecurity-20B-Merged-heretic-i1-GGUFQwen3.8-27B-Uncensored-GPTQ-Int4-sym-G128-MTP-BF16
