github.com/ollama/ollama

What's Changed

• Ollama's app now follows the system appearance again, restoring dark mode support
• Fixed the macOS app to properly hand off to an already-running instance instead of starting a second one
• The Claude Desktop proxy no longer interrupts in-flight requests when the model catalog updates

Full Changelog: v0.33.1...v0.33.2

app: list account cloud models for Claude (#18077)

app: synchronize macOS app handoff (#18056)

What's Changed

• MLX: Qwen3.8 Flash Next support
• cmake: make external compat patches idempotent
• MLX and llama.cpp update
• mlxrunner: add structured output support
• mlxrunner: avoid Metal GPU timeouts when loading models from slow storage

New Contributors

• @pd95 made their first contribution in #17948

Full Changelog: v0.33.0...v0.33.1

Build context was missing the new cmake common utility.

• MLX: Qwen3.8 Flash Next support

• review comments

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
• Prefill restore points are now trustworthy by construction: a cancelled prefill keeps every restore point it crossed, so retries resume where they stopped instead of restarting from scratch
• 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 npx 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: v0.32.15...v0.33.0

proxy: preserve string content during image fallback (#18002)

app: add Claude Desktop model mappings (#17979)

app: prevent Apps title bar overlap (#17925)

app: sign model recommendation endpoint (#17919)

app: claude model management (#17915)

What's Changed

• New desktop onboarding flow on first launch
• Caches resolved model metadata between requests, cutting time-to-first-token by roughly half (TTFT dropped from ~995 ms to ~524 ms in benchmarks)
• Fixes a bug where chat and generate could wedge after a mid-stream parser error
• Qwen 3.8 system messages are now normalized so non-leading system messages are handled consistently
• MLX and llama.cpp dependency updates

New Contributors

• @gaugarg-nv made their first contribution in #17752

Full Changelog: v0.32.14...v0.32.15

app: add desktop onboarding flow (#17853)

Follow up to #17850

Temporarily carry ml-explore/mlx-c#127

What's Changed

• llm: transcode WebP images for llama-server
• renderers/qwen: tolerate non-leading system messages

Full Changelog: v0.32.13...v0.32.14

mlx update (#17761)

What's Changed

• qwen3.8: support developer instructions

Full Changelog: v0.32.12...v0.32.13