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.
Qwen3.5-9B-DeepSeek-V4-Flash-GGUFQwopus3.8-27B-Flash-GGUFcanary-180m-flash-ggufcanary-1b-flash-ggufDeepSeek-V4.1-Flash-FP8-GGUFDeepSeek-V4-Flash-0731-REAM144-163B-DS4-GGUFGLM-5.3-Flash-FP8-GGUFQwen3.5-9B-DeepSeek-V4-Flash-GGUFDeepSeek-V4-Flash-0731-REAM96-111B-DS4-GGUFStep-3.7-Flash-GGUFcanary-1b-flashQwopus3.8-27B-FlashQwopus3.8-27B-Flash-i1-GGUFMLX-Qwen3.5-9B-DeepSeek-V4-Flash-4bitQwen3.8-Flash-Next-BF16-GGUFQwen3.5-9B-DeepSeek-V4-Flash-i1-GGUFcanary-180m-flashQwopus3.8-27B-Flash-GGUFLlama-3.3-8B-Thinking-Gemini-Flash-11000x-128k-i1-GGUFDeepSeek-V4-Flash-Vision-Exp-FP8-GGUFQwopus3.8-27B-Flash-INT4-W4A16qwen3.8-flash-next-40b-prune-researchGRaPE-2.1-Flash-i1-GGUFQwen3.5-9B-DeepSeek-V4-FlashQwopus3.8-27B-Flash-NVFP4GRaPE-2.1-Flash-GGUFqwopus3.8-27b-flash-mxfp4-vision-mtplxLlama-3.3-8B-Thinking-Gemini-Flash-11000x-128k-GGUFNovaciano-3.2-1B-FlashNorm-RP-FP16-i1-GGUFQwopus3.8-27B-Flash-AWQ-MTP
