# ollama/release
Ollama v0.40.15-rc1
v0.40.15
importance: highfeatureprerelease
This prerelease adds MiMo V2.6 model support. It also changes Linux MLX to load bundled CUDA libraries in-process.
affected
Users running Ollama on Linux with MLX or working with MiMo V2.6 models are affected.
release_signals
+Added support for the MiMo V2.6 model.
+Linux MLX now loads bundled CUDA libraries in-process.
# 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.