Blog · Signals · September 7, 2026
Signals: what shipped in local AI, week of September 7, 2026
12 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.
-
Ollamav0.34.02026-09-05
Use Ollama models in ChatGPT Desktop Ollama models can now be used directly in ChatGPT Desktop, so you can keep your existing workflow while running open models. Setup is available from the Ollama…
-
vLLMv0.29.0rc32026-09-04
[CI] Remove deleted nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF1…
-
vLLMv0.29.0rc4: [Bugfix] Avoid sync in TRT-LLM ragged prefill2026-09-04
Generated-by: Codex codex@openai.com Signed-off-by: Codex codex@openai.com
-
Ollamav0.34.0-rc02026-09-04
app: add Ollama to ChatGPT Desktop
Models
Open weights published in the open, newest first.
-
Trending GGUFJackrong/Qwopus3.8-27B-Flash-GGUF2026-09-04
60,343 downloads · 134 likes · gguf · text-generation
-
Trending GGUFIFM/K2-Horizon-MoVA-36B-A4B-GGUF2026-09-03
3,932 downloads · 80 likes · gguf · moe · text-generation
-
NVIDIA modelsnvidia/Qwen3.8-Flash-Next-NVFP42026-09-02
18,068 downloads · 129 likes
-
NVIDIA modelsnvidia/Muse-Glimmer-30B-NVFP42026-08-27
9,342 downloads · 6 likes
-
QwenQwen/Qwen-Drive-1.0-4B2026-08-27
985 downloads · 60 likes
Hardware and platform
The silicon and the runtime everything above depends on.
-
NVIDIA blogSparks Fly: NVIDIA Accelerates Local AI at IFA 20262026-09-03
Frontier intelligence is going local. At IFA 2026, NVIDIA, Microsoft and its partners are teaming up to provide faster inference and new tools that make agents easier to set up and run locally on…
-
Hugging Face blogBenchMIRT: What are LLM benchmarks actually measuring?2026-09-01
-
Hugging Face blogIntroducing @huggingface/kernels: 200+ WebGPU Kernels for Local AI2026-09-01
Sources
Every entry above links its own announcement. The feeds read this week:
- Ollama
- vLLM
- Trending GGUF
- NVIDIA models
- Qwen
- NVIDIA blog
- Hugging Face 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.