1I built two open-source tools to fix AMD GPU local LLM setup (ROCmFix) and benchmark Vulkan vs HIP performance (InferBench)Xanpavle@lemmy.worldEnglish · 2 days0 Comments
1old model: reaperdoesntknow/Qwen3-1.7B-Distilled-30B-A3B-SFTleanleft@lemmy.mlEnglish · huggingface.co · 6 days0 Comments
1old model: aifeifei798/QiMing-Moe-20B-MXFP4leanleft@lemmy.mlEnglish · huggingface.co · 6 days0 Comments
1llama.cpp v0.4.1 adds Maple 20B-A1B, Tencent Hy 4, and Spark2.5 support, improves JSON schema handling, chat parsing, logging, and server child-process management, and updates ggml to v0.24.0BeefAndPoultry@lemmus.orgEnglish · github.com · 6 days0 Comments
1old model: Jackrong/Negentropy-claude-opus-4.7-4Bleanleft@lemmy.mlEnglish · huggingface.co · 7 days0 Comments