# ollama/release
Ollama v0.40.15
importance: highmigrationfeature
Ollama adds support for Xiaomi’s MiMo V2.6 model and the AutoTrust decision-model family, including Apple silicon support for autotrust-jev. The release also expands launcher integrations, improves concurrent serving of recurrent and vision GGUF models, and opens the welcome launcher when Ollama is run without arguments.
affected
Ollama users, especially those using supported models, launcher integrations, or recurrent and vision GGUF models, can use the new model support and workflow improvements.
action
Run `ollama run mimo-v2.6` or `ollama launch` to try the new model and launcher integrations.
release_signals
+Support for MiMo V2.6, a 9B model for code and agent workflows.
+Support for AutoTrust decision models in 9B, 35B, and 27B-VL sizes; the 35B and 27B-VL models can read images. autotrust-jev is supported on Apple silicon.
+`ollama launch` supports Kimi Code CLI and offers to migrate existing kimi-cli setups.
+`ollama launch` automatically fills in Pi's model list, and Claude Desktop's model picker displays Ollama model names.
+Recurrent and vision GGUF models can serve multiple requests concurrently; Qwen3 and Qwen3.5 support long-context YaRN scaling, and running Ollama without arguments opens the welcome launcher.
migration_steps1 steps
- 01For existing kimi-cli setups, use the migration option offered by `ollama launch` to migrate to Kimi Code CLI.
code_snippet
ollama run mimo-v2.6# 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.