Canonical AI event

New version 0.34.1 raises token repeat limit to 100.

The gemma3n projector is now excluded from CPU usage. The app layout and command copy feedback have been refreshed.

14 Sept 20261 verified claims1 sources1 observations

What happened

The official source reports this update: v0.34.1. What's Changed app: fix ChatGPT model selector spacing mlxrunner: Evict prefix cache snapshots from the active conversation mlxrunner: check system free memory and wait for evicted runners before loading the next MLX model llm: raise token repeat limit to 100 and return error instead of incomplete result mlx: scope array lifetimes instead of pinning and sweeping llm: keep gemma3n projector off the CPU app: refresh Apps layout and command copy feedback MLX and llama.cpp updates Full Changelog : v0.34.0...v0.34.1-rc1

Why it matters

This official update documents a development concerning v0.34.1. Its practical significance depends on the scope and evidence stated by the source.

What to watch next

Read the official source update and verify its stated scope, evidence and timing before acting on it.

Connected knowledge