Skip to content

ollama

Model Serving & MLOps

A self‑hosted platform for running open‑source large language models locally

Go Latest v0.30.3 · 9h ago Security brief →

Features

  • Run open‑source LLMs locally via CLI or REST API
  • Support for multiple integrations (Claude Code, Codex, Copilot, OpenClaw, etc.)
  • Docker image available for containerized deployment

Recent releases

View all 49 releases →
No immediate action
v0.30.3 New feature

Gemma 4‑12B support

No immediate action
v0.30.2 Mixed

Cline CLI, Qwen integration, LLM improvements

No immediate action
v0.23.3 Bug fix

macOS 26 leak fix

v0.23.2 Breaking risk
⚠ Upgrade required
  • Use `ollama launch claude-desktop --restore` to re-enable Claude Desktop after upgrade.
Breaking changes
  • `ollama launch` no longer includes Claude Desktop
Notable features
  • /api/show responses are now cached, improving median latency by ~6.7x
  • Improved backup workflow when managing launch integrations
  • Cleaner image generation layout in the MLX runner
Full changelog

What's Changed

  • ollama launch no longer includes Claude Desktop due to the third-party integration being limited to Anthropic models.
  • Use ollama launch claude-desktop --restore to restore Claude Desktop to its normal state.
  • /api/show responses are now cached, improving median latency by ~6.7x which will increase load speed for integrations like VS Code.
  • Improved backup workflow when managing launch integrations
  • Cleaner image generation layout in the MLX runner

Full Changelog: https://github.com/ollama/ollama/compare/v0.23.1...v0.23.2

v0.23.1 New feature
Notable features
  • Gemma 4 MTP speculative decoding support on Macs (up to 2x speed increase for Gemma 4 31B coding tasks)
  • MLX and MLX-C updated with threading fixes
  • Go runtime bumped to version 1.26
Full changelog

Gemma 4 MTP (Multi-token Processing) for the MLX runner

Gemma 4 MTP speculative decoding is now supported on Macs. This can give over a 2x speed increase for the Gemma 4 31B model on coding tasks.

ollama run gemma4:31b-coding-mtp-bf16

What's Changed

  • Update MLX and MLX-C with threading fixes by @dhiltgen in https://github.com/ollama/ollama/pull/15845
  • go: bump to 1.26 by @ParthSareen in https://github.com/ollama/ollama/pull/15904
  • Add Gemma 4 MTP speculative decoding by @pdevine in https://github.com/ollama/ollama/pull/15980

Full Changelog: https://github.com/ollama/ollama/compare/v0.23.0...v0.23.1-rc0

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

About

Stars
172,921
Forks
16,399
Languages
Go C TypeScript

Install & Platforms

Install via
shell-script binary
Platforms
linux macos windows

Community & Support

Open source alternatives

Beta — feedback welcome: [email protected]