Ollama has released version 0.34.2, introducing a new first-run setup process that allows users to sign in or proceed locally. This setup is synchronized with the desktop application on macOS and Windows. The update also includes a direct link to the desktop app's Apps page via `ollama://apps` and resolves an issue with excessive memory growth during extended generations using MLX speculative decoding. Additionally, the release incorporates updates to llama.cpp. AI
IMPACT Improves the user experience and stability of the Ollama local LLM runner.
RANK_REASON This is a software update for a specific tool, not a frontier release or significant industry event.
Read on Mastodon — sigmoid.social →
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →