https://openmodelweights.com/news/nanbeige43-33b-open-agentic-teacher-model-20261027/Open Model Weightsen2026-10-27T07:24:38ZNanbeige opens a 33B agent model built to teach smaller models https://openmodelweights.com/news/qwen-audio-31-asr-speaker-diarization-20261027/Open Model Weightsen2026-10-27T07:24:38ZQwen extends speech recognition to speaker-aware audio analysis https://openmodelweights.com/news/sglang-unified-memory-hybrid-cache-20261027/Open Model Weightsen2026-10-27T07:24:38ZSGLang shares GPU memory across KV cache and recurrent states https://openmodelweights.com/news/llamacpp-deepseek-v41-flash-local-support-20261027/Open Model Weightsen2026-10-27T07:24:38Zllama.cpp adds a DeepSeek V4.1 Flash model path for local runtimes https://openmodelweights.com/news/krafton-raon-1-mini-30b-a4b-korean-open-moe-20261025/Open Model Weightsen2026-10-25T08:56:50ZKRAFTON opens Raon-1 mini, a 30B-class Korean coding and agent model https://openmodelweights.com/news/recursive-flint-40b-a25b-local-agentic-coding-20261025/Open Model Weightsen2026-10-25T08:56:50ZRecursive Flint makes its 40B sparse coding model a local-agent option https://openmodelweights.com/news/ollama-04011-local-phonon-speech-d3-decision-models-20261025/Open Model Weightsen2026-10-25T08:56:50ZOllama 0.40.11 brings streaming local speech and d3 decision models https://openmodelweights.com/news/huggingface-hub-230-live-bucket-follow-model-data-20261025/Open Model Weightsen2026-10-25T08:56:50ZHugging Face Hub 2.3.0 adds live Bucket updates for data pipelines