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.
GLM-5.3-Flash-Uncensored-Q2-ds4qwen3.8-27B-qat-q2_0-ggufDeepSeek-V4.1-Flash-UNCENSORED-DwarfStar-Q2Qwen3.8-27B-DFlash2-Q2_K_S-MIX-GGUFGLM-5.2-Q2_K-MTP-Q8-layersQwen3.8-27B-DFlash2-Q2_K-GGUFDeepSeek-V4.1-Flash-MTPLX-streaming-q2Q2.5-Veltha-14B-0.5-GGUFQ2.5-MS-Mistoria-72b-v2-GGUFGLM-5.3-Flash-Spark-Q2XL-MTPSharona_Q27B-R_CodeSecurity_v2Qwen3.8-27B-UD-Q2_K_XL-MLX-imatrix-directQ25-1.5B-VeoLu-GGUFDeepSeek-V4-Flash-0731-dwarfstar-q2-ggufDeepSeek-V4-Flash-MLX-Q2iKimi-K3-Q2_K-t158-MTPLXKimi-K3-Q2_K-t158-MTPLX-streamingSharona_Q27B-R_CodeSecurityDeepSeek-V4-Flash-MLX-Q2-mixed-gs128-affineBonsai-REDUX2-gguf-Q2_K-alteredalielfilali01-Q2AW1M-0001-GGUFQwen2.5-Coder-1.5B-Instruct-Q2_K-GGUFKIMI-K3-Q2_K-GGUF-ABLITERATEDalielfilali01-Q2AW1M-1111-GGUFalielfilali01-Q2AW1M-1010-GGUFalielfilali01-Q2AW1M-0010-GGUFvenice-uncensored-Q2_K-GGUFgemma-4-e2b-it-Q2_K-GGUFDeepSeek-V4-Pro-Preview-MLX-Q2iQwen3.6-35B-A3B-UD-Q2_K_XL-mlx
