Blog · Signals · November 2, 2026
Signals: what shipped in local AI, week of November 2, 2026
16 things shipped in local AI this week that we thought were worth knowing about. Every line below is a project's own announcement of its own work, linked back to where it was published.
What this page is. A machine collected these from release feeds and model registries and formatted them. It did not summarize, rank by opinion, or add commentary — the words in each entry are the publisher's own words, and the date is theirs too. That is the whole reason it is allowed to publish itself: there is nothing here for a machine to get wrong except the copying, and the link beside every line is how you check it. Inclusion is not endorsement, and nothing here has been tested by us. The pages where we do make claims about our own product are written by people and reviewed, and our own limits stay recorded in the Sovereignty Ledger.
Engines
The local runtimes SovereignAI talks to, and the ones it could.
-
llama.cppb12039: jinja : implement map('filter') (#24033)2026-11-02
jinja: implement map('filter') jinja : validate filter keyword arguments Assisted-by: Codex
-
vLLMv0.33.02026-11-02
v0.33.0 Highlights This release features 927 commits from 389 contributors (122 new)! New models : Reflection Beam-1.0 (501B MoE, 23B active) with its DFlash2 drafter, Yandex…
-
vLLMv0.33.02026-11-01
-
Ollamav0.40.132026-10-29
LFM3 on Linux and Windows Liquid AI's LFM3 models, including text-to-speech in lfm3-audio and lfm3-omni , now run on Linux and Windows as well as Apple silicon. Full Changelog : v0.40.12...v0.40.13
-
Ollamav0.40.13-rc02026-10-28
llama.cpp: version bump b11963
Models
Open weights published in the open, newest first.
-
NVIDIA modelsnvidia/DeepSeek-V4.1-Flash-1017-NVFP42026-10-30
1,839 downloads · 130 likes
-
Liquid AILiquidAI/d1-2B-GGUF2026-10-27
17,167 downloads · 28 likes · gguf
-
Liquid AILiquidAI/d1-2B-MLX-4bit2026-10-27
435 downloads · 6 likes
-
Trending GGUFLiquidAI/LFM3-Omni-2B-GGUF2026-10-27
132,215 downloads · 108 likes · gguf
-
NVIDIA modelsnvidia/Metatron-v12026-10-27
1,327 downloads · 11 likes
-
Trending GGUFccore/Qwen3.5-4B-3D-Coder2026-10-25
63,499 downloads · 544 likes · gguf
The local-first wave
Everyone else building a private AI you run yourself.
-
Jan0.8.82026-10-28
Jan v0.8.8: security fixes, llama.cpp 0.7.0, and Trusted Hosts for the local API A security update to v0.8.7. We recommend updating. Your data and settings carry over; a few behaviours change, listed…
Hardware and platform
The silicon and the runtime everything above depends on.
-
Hugging Face blognemotron-halloween2026-10-30
-
Node.js releases2026-10-29, Version 27.0.0-alpha.0.0.0 (Alpha), @RafaelGSS2026-10-29
Notable Changes V8 15.6 The V8 engine is updated to version 15.6.75.13, up from 14.6 in Node.js 26. Highlights: New language features enabled by default: Math.sumPrecise() ,…
-
Hugging Face blogIntroducing AnySpeechRecognizer and AnyDecisionModel: Open Models for Speech and Decisions on Apple Platforms2026-10-29
-
Node.js releases2026-10-28, Version 24.22.2 'Krypton' (LTS), @aduh952026-10-28
Commits [ f8bdcd54ed ] - deps : V8: backport 786c1c2d88d4 (Eliau Elkouby) #66249 [ 3b93fd6b2b ] - deps : V8: backport 1a0089053443 (Jakob Linke) #65764 [ 5aaf62faaa ] - deps : V8: backport…
Sources
Every entry above links its own announcement. The feeds read this week:
- llama.cpp
- vLLM
- Ollama
- NVIDIA models
- Liquid AI
- Trending GGUF
- Jan
- Hugging Face blog
- Node.js releases
The full source list, with a note on why each one is watched, is in the repository — as is the code that assembled this page. Nothing was fetched that is not in that file.