Tools · Updated 13 Oct, 12:30 am IST
Ollama publishes v0.40.4 with llama.cpp and server improvements
Why it matters for readers: It’s a routine upgrade that adds a new embedding model and fixes several backend issues.
- Updated llama.cpp to b11521 to support decision models and EmbeddingGemma 2.1
- Server changes reuse verified manifests and loaded models in inference routes.1
- MLX changes restore compact recurrent state after speculative rollback and bump MLX versions.1
- Launch/UI now includes installed models in the Codex /model picker.1
Get a brief like this every morning
Uzha reads hundreds of sources and gives you the stories that matter for your work, with every source linked. Free.
Get started