# Ollama releases v0.40.4‑rc0 with updated llama.cpp and model picker

> The open‑source Ollama server adds a newer llama.cpp core, reuses manifests for faster inference, and shows installed models in the UI.

Oossa · 2026-10-12 · https://oossa.com/en/ollama-releases-v0-40-4-rc0-with-updated-llama-cpp-and-model-picker

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.

## The facts

- Release date: 2026-10-12 ("Mon Oct 12 2026")
- llama.cpp updated to commit b11521; UI now shows installed models in the model picker

## Why it matters

Ollama users get quicker responses and a clearer view of which models they can run locally.

## Sources & references

1. [ollama/ollama v0.40.4](https://github.com/ollama/ollama/releases/tag/v0.40.4-rc0) – Ollama, 2026-10-12

Last updated: 2026-10-12