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.
Qwen3-Coder-30B-A3B-Instruct-SOTA-GGUFOpenCodeInterpreter-DS-6.7B-SOTA-GGUFgemma-4-31B-it-NVFP4-turbo-GGUFgorilla-openfunctions-v2-SOTA-GGUFQwen2.5-Coder-32B-Instruct-SOTA-GGUFMistral-Nemo-Instruct-2407-SOTA-GGUFQwen2.5-Coder-7B-Instruct-SOTA-GGUFCerebrum-1.0-8x7b-SOTA-GGUFMistral-7B-Instruct-v0.3-SOTA-GGUFgranite-3.2-8b-instruct-SOTA-GGUFYi-Coder-9B-Chat-SOTA-GGUFpydevmini1-SOTA-GGUFNxcode-CQ-7B-orpo-SOTA-GGUFCiSiMi-v0.1Qwen2.5-Coder-0.5B-Instruct-SOTA-GGUFmini-bart-g2pCodeQwen1.5-7B-Chat-SOTA-GGUFQwen3.5-4B-TMax-CISPObabylm_zho_pinyin_spmmr_midtrained_9b_v3_async_v2_cispo_step_150mr_midtrained_9b_v3_async_v2_cispo_step_127olmo3_cispoShi-Cis-Kestrel-uncensoredcisco-foundation-sec-cybersecCIS6930_DAAGR_GPT2_NoEmovicuna-160m-gptqwolof-qwen-1.5b-Q4_K_M-GGUFvicuna68_distilledCIS6930_DAAGR_GPT2_Emocisco-inam-merge