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.
Qwen2.5-32B-Instruct-GPTQ-Int4Qwen2.5-Coder-7B-Instruct-GPTQ-Int4Qwen2.5-14B-Instruct-GPTQ-Int4medgemma-27b-text-it-GPTQQwen3.6-27B-GPTQ-Pro-4bitQwen3.6-35B-A3B-GPTQ-Int4Qwen3.8-27B-EfficientThink-Uncensored-K3-Opus5-Grok4.6-GPT5.6Sol-SFT-SimPO-DFlash2-GGUFQwen3.8-27B-EfficientThink-Uncensored-K3-Opus5-Grok4.6-GPT5.6Sol-SFT-SimPO-DFlash2Qwen2.5-7B-Instruct-GPTQ-Int4Qwen3.8-27B-GPTQ-Int4-sym-G128-MTP-BF16gpt-oss-20b-OptiQ-4bitQwen2.5-Coder-14B-Instruct-GPTQ-Int4Qwen3.8-27B-GPTQ-Int4Qwen3.6-27B-GPTQ-Int4gemma-4-E4B-it-W4A16-AutoRound-GPTQblm-gpt2s-90M-s42_901M-s42_submissionApodex-1.1-mini-GPTQ-Int4Qwen1.5-72B-Chat-GPTQ-Int4Qwen2.5-72B-Instruct-GPTQ-Int4Qwen1.5-32B-Chat-GPTQ-Int4Meta-Llama-3.1-8B-Instruct-GPTQ-INT4GPT-oss-20B-RoleplaySFT-mxfp4-i1-GGUFQwen2.5-3B-Instruct-GPTQ-Int4airoboros-65b-gpt4-2.0-i1-GGUFQwen2-1.5B-Instruct-GPTQ-Int4Qwen1.5-4B-Chat-GPTQ-Int4GPT4-X-Alpasta-30b-i1-GGUFQwen3.8-27B-EfficientThink-Uncensored-K3-Opus5-Grok4.6-GPT5.6Sol-SFT-SimPO-DFlash2-GGUFairoboros-65b-gpt4-m2.0-i1-GGUFQwen3.8-27B-Uncensored-GPTQ-Int4-sym-G128-MTP-BF16
