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.
DeepSeek-V4-Flash-FP4-FP8-GGUFLTX-2.3-uncensored-v1.4-FP8krea2-turbo-uncensored-v1.1-FP8LTX-2.5-uncensored-v1.1-FP8DeepSeek-V4.1-Flash-FP8-GGUFgranite-4.1-8b-fp8Qwen3.8-27B-Uncensored-FP8-Q4_K_M-GGUFQwen3.8-27B-Uncensored-FP8-GGUFLTX-2.5-uncensored-v1.1-FP8Bielik-11B-v3.0-Instruct-FP8-DynamicGLM-5.3-Flash-FP8-GGUFLTX-2.3-uncensored-v1.4-FP8DeepSeek-V4-Flash-Vision-Exp-FP8-GGUFQwen3.8-27B-Uncensored-FP8-i1-GGUFFlux-Fusion-DS-merge-gguf-nf4-fp4-fp8-fp16Qwen3.6-35B-A3B-FP8-Q4_K_M-MTP-GUFFwan22-fp8-i2v-ggufgranite-4.1-30b-fp8Qwen3.8-Flash-Next-FP8-Abliterated-GGUFgranite-4.1-3b-fp8Llama-4-Scout-Medical-MoE-fp8-base-i1-GGUFQwopucode-full-v15-27B-FP8-Block-i1-GGUFBielik-4.5B-v3.0-Instruct-FP8-DynamicQwen3.8-27B-Uncensored-FP8-i1-GGUFOrnith-1.0-35B-FP8-BLOCK-MTP-i1-GGUFchandra-FP8-Latest-i1-GGUFgranite-4.0-h-small-FP8Qwen3-Coder-30B-A3B-Instruct-FP8-Q4_K_M-GGUFamd_-_Meta-Llama-3-8B_fp8_quark-ggufBielik-1.5B-v3.0-Instruct-FP8-Dynamic
