The name is the button.

An agent writes the code now, and a human thumb hovers over Accept all a hundred times a day. The honest question of this decade is what, exactly, you just accepted. So I read the diff.

Eight years as a backend engineer in Stockholm, back in Tokyo since 2023, and I still ship something small most nights, usually badly. My one rule: the only real review of a model is the thing you built with it. That is why there is no leaderboard on this site.

Around a hundred and forty sources come through — the labs' own posts, the papers, the tools, the runtimes and languages nobody is watching yet, the chip under the demo, and the newsletters people actually forward. What is moving gets counted so the week reads at a glance, and every few days I explain one mechanism in plain words.

A story here is a headline, a short excerpt, one image and the link to whoever wrote it. We never reproduce the post; the images belong to their authors. A post written in Japanese appears in Japanese, exactly as it was published, and the link goes to the original.

— Yuki Halvorsen, Tokyo

← Accept All Archive

Qiita (LLM)Japan

同じGGUFなのにLM Studio 6.2 tok/s → Ollama 19.1 tok/s。VRAM 8GBでQwen3.6-35B-A3Bを実測した

10.22

RTX 3060 Ti（VRAM 8GB）のPCで、35B の MoE モデル Qwen3.6-35B-A3B を動かしています。 LM Studio で使っていて「遅いな」と思っていたのですが、まったく同じ GGUF ファイルを Ollama に読み込ませたら、生成速...

Models & releases Open weights

Read at Qiita (LLM) ↗

One letter a week, starting soon.

Latest

同じGGUFなのにLM Studio 6.2 tok/s → Ollama 19.1 tok/s。VRAM 8GBでQwen3.6-35B-A3Bを実測した

Related

Japan【見逃し厳禁！】AI個人開発で賞金を狙え！総額20,000ドル＆25ドル分クレジットのBeamコンテスト！ Qiita (LLM)

GitHubDeveloper Behind the AI-Built Adobe Clones Says They Are “Not Anywhere Close to Ready InfoQ AI

AsiaAnyverse Dynamics Open-Sources MWA-Phoenix, a 7B On-Device World Action Model for Robots Pandaily

GitHubShow HN: Omnara – Open-source alternative to Claude Managed Agents Hacker News Show

DeepSeek makes DeepInfer open source to cut AI costs AI Business

AsiaDeepSeek open-sources inference framework with support for Nvidia and Huawei chips TechNode