llmfan46/Qwen3.8-27B-Uncensored-Heretic-Native-MTP-Preserved-NVFP4 Image-Text-to-Text • 27B • Updated Aug 31 • 1.4k • 2
llmfan46/Qwen3.8-27B-Uncensored-Heretic-Native-MTP-Preserved Image-Text-to-Text • 27B • Updated Aug 31 • 773 • 20
llmfan46/gemma-4-31B-it-uncensored-heretic-GGUF Image-Text-to-Text • 31B • Updated Jun 30 • 83.4k • 210
llmfan46/MiniMax-M2.7-ultra-uncensored-heretic-GGUF Text Generation • 229B • Updated Jun 17 • 15.8k • 29
100 Coder/Programming - MOE, Reasoning, Reg, Imatrix, Fused. Collection Models (0.8B to 87B) in regular, "reasoning", "Brainstorm", MOE (1x to 8x / 128 experts), and expanded to create better and stronger code, faster. • 85 items • Updated 9 days ago • 75
view article Article Mixture of Experts Explained +4 osanseviero, lewtun, philschmid, smangrul, ybelkada, pcuenq • Dec 11, 2023 • 1.21k
view article Article Performant local mixture-of-experts CPU inference with GPU acceleration in llama.cpp Doctor-Shotgun • Jan 30 • 33
view article Article Liberate your OpenClaw +6 clem, burtenshaw, pcuenq, jeffboudier, merve, nielsr, victor, mishig • Mar 27 • 52