Ollama - Package Updates

[Package Updates]

[1.15.5]

• Update ollama to 0.32.6
• Full Changelog
• Qwen3.5 is faster on Apple GPUs: the MLX engine now uses the model's MTP head for speculative decoding automatically
• /v1/chat/completions streaming now matches OpenAI's wire format: role only on the first chunk, finish_reason on its own chunk,
• and usage in a separate chunk with stream_options.include_usage.
• Truncated OpenAI responses now report finish_reason: "length" instead of "tool_calls".
• ollama run kimi-k3 now offers kimi-k3:cloud for cloud-only models that publish no default tag, instead of failing.
• TUI fixes: pipe-delimited prose no longer renders as a table, Enter accepts the highlighted @ file completion, and /prompt
• scrolling is no longer laggy.
• Experimental image generation has been temporarily removed. Continue using 0.32.5 for image generation support
• Updated the MLX and llama.cpp engines.
• Full Changelog: https://github.com/ollama/ollama/compare/v0.32.5...v0.32.6-rc0

[Package Updates]

[1.15.6]

• Update ollama to 0.32.7
• Full Changelog
• Muse Glimmer, Meta's newest open model and the first released by Meta Superintelligence Labs, is now available on Ollama. It's a 30B multimodal model purpose-built for agent workloads that run locally.
• With Ollama, you can now use Muse Glimmer to power coding agent applications such as Claude Code, Codex, Pi and more, as well as long-running personal assistants such as OpenClaw and Hermes.
• Ollama's MLX engine provides state-of-the-art performance on Apple Silicon for this model, with support for DFlash and image input as of Ollama 0.32.7.

[Package Updates]

[1.15.7]

• Update ollama to 0.32.9
• Full Changelog
• Added the Nemotron 3 architecture
• Handle boundary condition in Muse Glimmer function calling parser
• Add Muse Glimmer support for NVIDIA, AMD, and additional platforms

[Package Updates]

[1.15.8]

• Update ollama to 0.32.14
• Full Changelog
• llm: transcode WebP images for llama-server
• renderers/qwen: tolerate non-leading system messages

[Package Updates]

[1.15.9]

• Update ollama to 0.32.15
• Full Changelog
• 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
• @gaugarg-nv made their first contribution in #17752

[Package Updates]

[1.16.0]

• Update ollama to 0.33.0
• Full Changelog
• Developers can now easily configure Claude Desktop to seamlessly work with Ollama as a third-party gateway provider.
• 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
• 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

[Package Updates]

[1.16.1]

• Update ollama to 0.33.1
• Full Changelog
• MLX: Qwen3.8 Flash Next support
• MLX and llama.cpp update
• mlxrunner: add structured output support
• mlxrunner: avoid Metal GPU timeouts when loading models from slow storage

[Package Updates]

[1.16.2]

• Update ollama to 0.33.2
• Full Changelog
• 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: https://github.com/ollama/ollama/compare/v0.33.1...v0.33.2

[Package Updates]

[1.16.3]

• Update ollama to 0.33.3
• Full Changelog
• gemma4 now supports images and audio on MLX engine
• Report cached prompt tokens
• Honor GGUF model defined default parameters
• MLX, MLX-C, llama.cpp update
• @marcelpetrick made their first contribution in #17579.3)

[Package Updates]

[1.17.0]

• Update ollama to 0.34.0
• Full Changelog
• Ollama models can now be used directly in ChatGPT Desktop, so you can keep your existing workflow while running open models. Setup is available from the Ollama app on MacOS.
• This release also improves structured output performance on Apple Silicon, adds support for OpenAI-compatible client tool search and response compaction.
• Full Changelog: https://github.com/ollama/ollama/compare/v0.33.3...v0.34.0

[Package Updates]

[1.17.1]

• Update ollama to 0.34.1
• Full Changelog
• MLX safetensors ollama create no longer experimental. GGUF model creation now requires using llama.cpp tooling for safetensor conversion and quantization.
• Improved MLX memory handling on Apple Silicon
• Runaway repeat token detection now requires 100 repeat tokens for reduced false positives (e.g. OCR)
• /api/tags is much faster on large model libraries (3.1 s 294 ms cold in testing), and model capabilities are now reported consistently.
• Deprecated typical_p: it can no longer be set when creating new models, existing GGUF models retain support.
• MLX and llama.cpp updates
• Full Changelog: https://github.com/ollama/ollama/compare/v0.34.0...v0.34.1-rc1