Ollama v0.40.4

v0.40.4
Added 3
  • Decision models can now be used directly from the CLI with `ollama run`, for yes/no questions, text classification, and rubric scoring
  • Decision models are now supported by the MLX runner on Apple silicon
  • Support added for multimodal embeddings through llama-server
Changed 8
  • `ollama launch` can now be used with usage credits without upgrading to a paid plan
  • `ollama launch codex` now includes locally installed Ollama models in its model picker, and `/model` within the Codex CLI can be used to swap models
  • Inference performance improved by reusing verified manifests and already loaded models
  • Gemma 4 prefill performance improved on NVIDIA GPUs with the MLX runner
  • MLX runner now clips long Laya states instead of rejecting them
  • Speculative decoding reliability improved in the MLX runner, including recurrent state handling after rollback
  • llama.cpp updated with native decision model support
  • README and documentation updated with clearer privacy and cloud-services wording
Fixed 1
  • Loading multimodal embedding models with small context windows is fixed

From Ollama

Decision models in the CLI

Decision models can now be used directly from the terminal with ollama run — ask yes/no questions, classify text into labels, or score against a rubric: ollama run nimble --ask "Is a refund being requested?" < ticket.txt

What's Changed
  • Kev decision models are now supported by the MLX runner on Apple silicon
  • ollama launch can now be used with usage credits without upgrading to a paid plan
  • ollama launch codex now includes locally installed Ollama models in its model picker. Use /model within the Codex CLI to swap models.
  • Improved inference performance by reusing verified manifests and already loaded models
  • Added support for multimodal embeddings through llama-server
  • Fixed loading multimodal embedding models with small context windows
  • Improved Gemma 4 prefill performance on NVIDIA GPUs with the MLX runner
  • MLX runner now clips long Laya states instead of rejecting them
  • Improved speculative decoding reliability in the MLX runner, including recurrent state handling after rollback
  • Updated llama.cpp with native decision model support
  • Updated README and documentation with clearer privacy and cloud-services wording

Full Changelog: https://github.com/ollama/ollama/compare/v0.40.3...v0.40.4

View original

Upgraded? How did it go?

Discussion