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.
moziAI-35B-A3B-MOE-MTPQwen2.5-MOE-2X1.5B-DeepSeek-Uncensored-Censored-4B-ggufQwen2.5-MOE-2X7B-DeepSeek-Abliterated-UNCensored-19B-ggufQwen3-MOE-4x0.6B-2.4B-Writing-ThunderLlama3.1-MOE-4X8B-Gated-IQ-Multi-Tier-Deep-Reasoning-32B-GGUFQwen3-MOE-6x0.6B-3.6B-Writing-On-Fire-Uncensored-Q8_0-GGUFISOM-R1-Coder-16B-MoE-BetaLlama3.1-MOE-4X8B-Gated-IQ-Multi-Tier-COGITO-Deep-Reasoning-32B-GGUFQwen3.6-35B-A3B-MXFP4-MOE-NoMTP-GGUFQwen3-MOE-6x0.6B-3.6B-Writing-On-Fire-UncensoredQwen3.6-35B-A3B-MXFP4-MOE-GGUFQwen3.8-27B-chinese-taste-sft-loraQwen3-MOE-4x0.6B-2.4B-Writing-Thunder-V1.2Elly-768-MoE-4bitdeepseek-moe-16b-q4-k-m-cpu-offload-ggufQwen3.5-122B-A10B-MXFP4_MOE-MTP-GGUFQwen3-MOE-6x1.7B-10.2B-Shining-Madness-UncensoredQwen3-MOE-4x0.6B-2.4B-Writing-Thunder-V1.2-q8-mlxQwen3-MOE-4x0.6B-2.4B-Writing-Thunder-V1.2-mlx-4BitMoE-Qwen-4x1.8B-pretrain-50000-ckptQwen3-MOE-4x1.7B-6.8B-Lucys-Song-UncensoredRain-2x7B-MoE-32k-v0.1-GGUFLlama3.1-MOE-4X8B-Gated-IQ-Multi-Tier-Deep-Reasoning-32Bdeepseek-moe-16b-q8-0-cpu-offload-ggufMiniMind-MoE-640-120MGLM-4.7-Flash-MXFP4-MOE-GGUFUni-MoE-2.0-OmniEastAsia-4x7B-Moe-experimentQwen3-14B-Moebius-qx86-hi-mlxQwen2.5-MOE-2X7B-DeepSeek-Abliterated-UNCensored-19B-gguf