Disaggregated Quantization: Specializing LLM Prefill and Decode Paper • 2609.26333 • Published Sep 22 • 95
Running 31 Weight-Space Geometry of Offline Reasoning Training 🧭 31 Interactive weight-space geometry of six reasoning losses
bartowski/cognitivecomputations_Dolphin-Mistral-24B-Venice-Edition-GGUF Text Generation • 24B • Updated Jul 7, 2025 • 30.1k • 173
lmstudio-community/Qwen3-Coder-30B-A3B-Instruct-MLX-8bit Text Generation • 31B • Updated Jul 31, 2025 • 72.9k • 26
lmstudio-community/Qwen3-30B-A3B-Instruct-2507-MLX-8bit Text Generation • 31B • Updated Jul 29, 2025 • 14.7k • 3