{"type":"post","id":"mlx-serve-v26-11-1-adds-installable-model-3f3b35","slug":"mlx-serve-v26-11-1-adds-installable-model-3f3b35","title":"mlx-serve v26.11.1 adds installable model plugins and faster DeepSeek-V4.1-Flash inference on Apple Silicon Macs","description":"mlx-serve v26.11.1 adds an experimental plugin workflow for extending model support and reports faster DeepSeek-V4.1-Flash inference on Apple Silicon Macs.","retrieval_nugget":"mlx-serve v26.11.1 adds an experimental plugin workflow for extending model support and reports faster DeepSeek-V4.1-Flash inference on Apple Silicon Macs. For teams running local models, the release points to a more extensible serving setup, but its speed claims are qualitative and the plugin system is explicitly experimental.","published_at":"2026-11-02","updated_at":"2026-11-02","record_date":"2026-11-02","date_kind":"published_at","topics":["codex"],"entities":["mlx-serve","DeepSeek-V4.1-Flash","Apple MLX","CommunityServe","Idol","LFM3","Nemotron 3.5 Transcribe","Codex"],"related_patterns":["harness-architecture-outlives-model-choice"],"novelty_label":"new_fact","what_changed":"mlx-serve v26.11.1 adds installable model plugins and faster DeepSeek-V4.1-Flash inference, a distinct runtime release from the prior Apple-silicon inference and plugin updates.","prior_refs":["https://newruntime.com/posts/omlx-0-7-3-speeds-up-deepseek-v4-fd0577/"],"source_url":"https://github.com/ddalcu/mlx-serve/releases/tag/v26.11.1","source_urls":["https://github.com/ddalcu/mlx-serve/releases/tag/v26.11.1"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:mlx-serve-v26-11-1-adds-installable-model-3f3b35","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/mlx-serve-v26-11-1-adds-installable-model-3f3b35/","markdown":"https://newruntime.com/posts/mlx-serve-v26-11-1-adds-installable-model-3f3b35.md","json":"https://newruntime.com/posts/mlx-serve-v26-11-1-adds-installable-model-3f3b35.json"},"markdown_url":"https://newruntime.com/posts/mlx-serve-v26-11-1-adds-installable-model-3f3b35.md","next_reads":[{"type":"topic","path":"/topics/codex/","url":"https://newruntime.com/topics/codex/","title":"Codex","reason":"Explore the codex topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/codex.md","json_url":"https://newruntime.com/topics/codex.json"},{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/sources/","url":"https://newruntime.com/sources/","title":"Sources","reason":"See the original sources this archive cites.","media_type":"text/html"}]}