MLX-Serve v26.11.3 ships with GLM 5.3 Flash streaming, Ming Speech and external plugins
HankYeomans · x · 2026-11-20
Local LLM serving project MLX-Serve released v26.11.3, adding Quick Create, H3 Image and Flash, Ming Speech support, steadier memory management, more models, and an external plugin mechanism. The update includes GLM 5.3 Flash streaming support, with a contributor list of 20+ community members.
More from Infra
- Baseten breaks down its security threat model as agent swarms accelerate attacks — baseten · 2026-11-21
- Nvidia's rivals are vying to be the 'Central Bank' of AI, says investor — GavinSBaker · 2026-11-21
- Benchmarking 11 open models' post-GQA attention: up to 139x less memory at 128K — bariskasikci · 2026-11-21
- Anthropic files for Nasdaq IPO — why you should keep a local open-source LLM as backup — alex_verem · 2026-11-21
- Microsoft launches MAI Licensed Weights; Purdue researcher asks to run them on own hardware — marlene_zw · 2026-11-21
- Looped CED cuts KV-cache memory 36.8x on 552B model, but encoder loops cost compute — teortaxesTex · 2026-11-21