view post Post 8410 1440GB of VRAM is incredibly satisfying 😁 See translation 17 replies · 🔥 27 27 👀 10 10 ❤️ 4 4 🤯 2 2 + Reply
view article Article GGML and llama.cpp join HF to ensure the long-term progress of Local AI +4 20 days ago • 480
huihui-ai/Huihui-Qwen3-Coder-Next-abliterated Text Generation • Updated about 1 month ago • 2.09k • 39
view article Article Geometric Manifold Walking: Stable High-Accuracy Multi-Encoder Fusion Without Backbone Training Dec 25, 2025 • 3
FiditeNemini/qwen3-48b-a4b-savant-commander-distill-12x-closed-open-heretic-uncensored-mlx-mxfp4 Text Generation • 434 • Updated Dec 22, 2025 • 11
FiditeNemini/qwen3-48b-a4b-savant-commander-distill-12x-closed-open-heretic-uncensored-mlx-mxfp4 Text Generation • 434 • Updated Dec 22, 2025 • 11
DavidAU/Qwen3-48B-A4B-Savant-Commander-Distill-12X-Closed-Open-Heretic-Uncensored-GGUF Text Generation • 34B • Updated Jan 6 • 2.73k • 33
DavidAU/Qwen3-48B-A4B-Savant-Commander-GATED-12x-Closed-Open-Source-Distill-GGUF Text Generation • 34B • Updated Jan 6 • 342 • 19
huihui-ai/Huihui-Qwen3-Next-80B-A3B-Instruct-abliterated Text Generation • 81B • Updated Dec 10, 2025 • 1.23k • 13
Mistral Large 3 Collection A state-of-the-art, open-weight, general-purpose multimodal model with a granular Mixture-of-Experts architecture. • 4 items • Updated Dec 2, 2025 • 94
view article Article How MCP Blockly Makes MCP Server Creation Accessible for Everyone Nov 28, 2025 • 9