The open‑source Ollama server adds a newer llama.cpp core, reuses manifests for faster inference, and shows installed models in the UI.
NoteBy OossaPublished by Oossa: 1 min read
Ollama published version 0.40.4‑rc0 on 12 October 2026. The update bumps llama.cpp to commit b11521, which improves decision‑model performance and adds EmbeddingGemma 2. The server now reuses verified manifests and loaded models, which can speed up inference routes. The launch UI also lists installed models in the Codex model picker, making it easier to see what’s available.
Ollama users get quicker responses and a clearer view of which models they can run locally.
Models
Meta's new Muse Wonder and Muse Wonder Full models rank among the best frontier AIs, but they cost more per token.
Models
AMD's Helion reference rack can hold 32,768 Zen 6 cores and will be available in CPU‑only and all‑in‑one versions next year.
Models
Vals AI’s study shows multi‑agent setups can spend up to five times the tokens of a single model for only tiny quality gains.
Oossa · Newsletter
The week in AI, explained
Every Monday: the stories worth knowing, in plain language. Free, no spam.
