Blog · Signals · October 12, 2026
Signals: what shipped in local AI, week of October 12, 2026
19 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.cppb11568: examples : fix draft sampling and rejection handling (#30095)2026-10-12
examples : fix draft sampling and rejection handling This commit fixes two issues in the speculative example which are described in detail in the linked issue. Resolves: #29975 examples : add…
-
Ollamav0.40.32026-10-11
What's Changed ollama launch claude no longer shows a warning about Claude connectors by @hoyyeva in #18878 ollama launch codex no longer warns about service tiers by @hoyyeva in #18879 Paused…
-
vLLMproto-v0.5.02026-10-09
-
Ollamav0.40.22026-10-09
Model upgrades Models downloaded with earlier versions of Ollama are upgraded in the background the first time you run them, for better performance and compatibility when running on llama.cpp. To…
-
vLLMv0.31.1rc0: [Metrics] Expose cached prompt tokens by cache tier (#56318)2026-10-06
Signed-off-by: Cam Quilici cjquilici@gmail.com Signed-off-by: Cam Quilici cameron@semianalysis.com
Models
Open weights published in the open, newest first.
-
Liquid AILiquidAI/d1-3B-MLX-4bit2026-10-12
8 downloads
-
Liquid AILiquidAI/d1-3B-MLX-8bit2026-10-12
7 downloads
-
NVIDIA modelsnvidia/agile_one_s_pick_ssd_n2_11202026-10-10
1 likes
-
NVIDIA modelsnvidia/agile_one_s_pickplace_ssd_n2_182002026-10-10
-
QwenQwen/Qwen-Image-2.1-Turbo2026-10-09
6,787 downloads · 607 likes
-
Trending GGUFConwayResearch/Underdog-Saluki-27B-1.02026-10-08
242,329 downloads · 357 likes · gguf · text-generation
-
Trending GGUFunsloth/embeddinggemma-2-GGUF2026-10-06
71,914 downloads · 275 likes · gguf
-
Google open weightsgoogle/embeddinggemma-22026-09-14
115,763 downloads · 1889 likes
The local-first wave
Everyone else building a private AI you run yourself.
-
Jan0.8.62026-10-09
Jan v0.8.6: hotfix for v0.8.5 Fixes only. If you're on 0.8.5, updating is recommended, especially on Linux (AppImage) and on older NVIDIA GPUs. Fixes Linux AppImage crashed on every model load on…
-
Jan0.8.52026-10-08
This release is fixes only No new features are announced in v0.8.5. Work in progress stays in the nightly channel: Cowork and the current agent work ship there until they are announced, and a stable…
Hardware and platform
The silicon and the runtime everything above depends on.
-
Node.js releases2026-10-07, Version 26.11.0 (Current), @aduh952026-10-07
Notable Changes [ 232f178825 ] - (SEMVER-MINOR) buffer : add isLatin1 (James M Snell) #66298 [ 27778036de ] - (SEMVER-MINOR) buffer : add Buffer.stringLength() (Matteo Collina) #66064 [ 4f84c4bda2 ]…
-
Node.js releases2026-10-07, Version 26.11.1 (Current), @aduh952026-10-07
Commits [ 2dc4638e85 ] - Revert " build : toggle doc-kit verbosity based on V" (Antoine du Hamel) [ 3febbc54ec ] - Revert " build, doc : move to redesign" (Antoine du Hamel) [ 173250e2e7 ] - Revert "…
-
Hugging Face blogOne Model Family, Two Gold-Level Results: Fine-Tuning Nemotron for IOI and IMO2026-10-07
-
NVIDIA blogWhy Telecom Operators Are Building Their AI Strategy on Open Models2026-10-06
Telecom operators are increasingly building their AI strategies on open models — and the reasons go beyond mere cost. Open models give telcos the ability to trust, control and customize AI across…
Sources
Every entry above links its own announcement. The feeds read this week:
- llama.cpp
- Ollama
- vLLM
- Liquid AI
- NVIDIA models
- Qwen
- Trending GGUF
- Google open weights
- Jan
- Node.js releases
- Hugging Face blog
- NVIDIA blog
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.