# ollama/release
Ollama v0.40.5
importance: highfeature
This release introduces support for NVIDIA Nemotron 3.5 Super, a vision-language model for coding and reasoning, and includes updates to decision models, error handling, and dependencies like llama.cpp and MLX.
affected
Users leveraging vision-language models or cloud-based decision models are most affected by this release.
action
Update to v0.40.5 to access new features and improvements.
release_signals
+Added support for NVIDIA Nemotron 3.5 Super, a vision-language model with a 120B-parameter hybrid Mamba-2/Transformer backbone.
+Decision models are now available on cloud via `clef:cloud` and `clef-flash:cloud`.
+Improved error messages for cloud access failures, including sign-in and payment issues.
+Updated llama.cpp to support Nemotron 3.5 and MLX.
code_snippet
ollama run nemotron-3.5-super# community_signal
How useful is this release to your stack?
—
net score
Sign in with GitHub to cast your vote.
Sign in with GitHub to vote
You’ll return to this release, then choose your vote.