← Back to Model Beat
Models·Aug 21·all news from August 21, 2026

ollama v0.33.0

## What's Changed ### Claude Desktop Developers can now easily configure Claude Desktop to seamlessly work with Ollama as a third-party gateway provider. ### Improved caching * Fixed a hang where agent clients that cancel long prefills * Resumed prefills no longer record restore points that fail to cover what they claim; on models with recurrent layers this previously forced a request matching 46k of 47k tokens to reprocess from zero * Disabled Claude Code's "tokens left" token-countdown system message, which Ollama moved to the front of the prompt and broke the KV cache on every request ### Other improvements * DeepSeek Harness launcher now falls back to when the global npm install fails, with Windows command-shim support * MLX dependency update (#17886) * Fixed broken default packaging caused by macOS-specific assumptions affecting Linux/Windows builds **Full Changelog**: https://github.com/ollama/ollama/compare/v0.32.15...v0.33.0

Covered by 1 source

Related stories

ModelsAlibaba Releases Smaller, Cost-Effective Qwen AI ModelAug 25 · 26 sourcesModelsDeepSeek Unveils Test Model to Rival Anthropic’s Opus 4.8Aug 19 · 16 sourcesModelsChinese Hackers Use DeepSeek to Boost Attacks, Researchers SayAug 24 · 23 sourcesModelsIntroducing ChatGPT for Teens: Built for learning, backed by protectionsAug 18 · 7 sources