-
GiteaMirror released this
2026-05-07 12:46:18 -05:00 | 21 commits to main since this release📅 Originally published on GitHub: Thu, 07 May 2026 20:23:10 GMT
🏷️ Git tag created: Thu, 07 May 2026 17:46:18 GMTWhat's Changed
ollama launchno longer includes Claude Desktop due to the third-party integration being limited to Anthropic models.- Use
ollama launch claude-desktop --restoreto restore Claude Desktop to its normal state. /api/showresponses 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
Downloads
-
2026-05-05 10:55:04 -05:00 | 26 commits to main since this release📅 Originally published on GitHub: Tue, 05 May 2026 17:13:31 GMT
🏷️ Git tag created: Tue, 05 May 2026 15:55:04 GMTGemma 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-bf16What'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
Downloads
-
2026-05-02 21:19:57 -05:00 | 29 commits to main since this release📅 Originally published on GitHub: Sun, 03 May 2026 03:34:11 GMT
🏷️ Git tag created: Sun, 03 May 2026 02:19:57 GMTClaude Desktop with Ollama Launch
Claude Desktop is now supported with Ollama Launch. Both Claude Cowork and Claude Code are supported within the Claude Desktop App.
ollama launch claude-desktopClaude Code on the terminal can still be accessed through the CLI with:
ollama launch claudeWhat's Changed
- Launch Claude Desktop with
ollama launch claude - The Ollama app now surfaces featured models from server-driven recommendations
- Fixed OpenClaw gateway timeout on Windows by enforcing IPv4 loopback - @UniquePratham
- Hardened Metal initialization to gracefully handle ggml kernel compilation failures
New Contributors
- @UniquePratham made their first contribution in https://github.com/ollama/ollama/pull/15726
Full Changelog: https://github.com/ollama/ollama/compare/v0.22.1...v0.23.0
Downloads
- Launch Claude Desktop with
-
2026-04-29 20:40:23 -05:00 | 34 commits to main since this release📅 Originally published on GitHub: Tue, 28 Apr 2026 20:30:57 GMT
🏷️ Git tag created: Thu, 30 Apr 2026 01:40:23 GMTWhat's Changed
- Updated the Gemma 4 renderer for thinking and tool calling improvements
- Model recommendations are now updated without updating Ollama
- Aligned the desktop app's launch page with
ollama launchintegrations - Fixed the Poolside integration title in
ollama launch
Full Changelog: https://github.com/ollama/ollama/compare/v0.22.0...v0.22.1
Downloads
-
2026-04-27 21:26:08 -05:00 | 36 commits to main since this release📅 Originally published on GitHub: Tue, 28 Apr 2026 15:00:25 GMT
🏷️ Git tag created: Tue, 28 Apr 2026 02:26:08 GMTNew models
- NVIDIA's Nemotron 3 Omni
- Poolside's first open-weight coding model - Laguna XS.2
Full Changelog: https://github.com/ollama/ollama/compare/v0.21.2...v0.22.0
Downloads
-
2026-04-24 04:49:36 -05:00 | 48 commits to main since this release📅 Originally published on GitHub: Fri, 24 Apr 2026 12:15:38 GMT
🏷️ Git tag created: Fri, 24 Apr 2026 09:49:36 GMTWhat's Changed
- api: accept "max" as a think value by @ParthSareen in https://github.com/ollama/ollama/pull/15787
- openai: map responses reasoning effort to think by @ParthSareen in https://github.com/ollama/ollama/pull/15789
Full Changelog: https://github.com/ollama/ollama/compare/v0.21.2...v0.21.3-rc0
Downloads
-
2026-04-23 18:47:20 -05:00 | 50 commits to main since this release📅 Originally published on GitHub: Thu, 23 Apr 2026 02:29:24 GMT
🏷️ Git tag created: Thu, 23 Apr 2026 23:47:20 GMTWhat's Changed
- Improved reliability of the OpenClaw onboarding flow in
ollama launch - Recommended models in
ollama launchnow appear in a fixed, canonical order - OpenClaw integration now bundles Ollama's web search plugin in OpenClaw
New Contributors
- @madflow made their first contribution in https://github.com/ollama/ollama/pull/15733
Full Changelog: https://github.com/ollama/ollama/compare/v0.21.1...v0.21.2
Downloads
- Improved reliability of the OpenClaw onboarding flow in
-
2026-04-21 17:13:20 -05:00 | 55 commits to main since this release📅 Originally published on GitHub: Wed, 22 Apr 2026 00:18:02 GMT
🏷️ Git tag created: Tue, 21 Apr 2026 22:13:20 GMTWhat's Changed
- docs: update hermes by @ParthSareen in https://github.com/ollama/ollama/pull/15655
- mlx: apply repeat penalties in sampler by @dhiltgen in https://github.com/ollama/ollama/pull/15631
- mlx: fuse sigmoid router head in glm4_moe_lite by @jessegross in https://github.com/ollama/ollama/pull/15659
- launch: add kimi cli integration with installer flow by @ParthSareen in https://github.com/ollama/ollama/pull/15723
- server: apply format when think=false with thinking-capable parser by @ParthSareen in https://github.com/ollama/ollama/pull/15678
Full Changelog: https://github.com/ollama/ollama/compare/v0.21.0...v0.21.1-rc0
Downloads
-
2026-04-16 19:18:04 -05:00 | 68 commits to main since this release📅 Originally published on GitHub: Thu, 16 Apr 2026 22:00:17 GMT
🏷️ Git tag created: Fri, 17 Apr 2026 00:18:04 GMTHermes Agent
ollama launch hermesHermes learns with you, automatically creating skills to better serve your workflows. Great for research and engineering tasks.
What's Changed
- Gemma 4 on MLX. Added support for running Gemma 4 via MLX on Apple Silicon, including a text-only MLX runtime for the model. The MLX backend also picked up mixed-precision quantization, better capability detection, and a batch of new op wrappers (Conv2d, Pad, activations, trig, masked SDPA, and RoPE-with-freqs).
- Hermes and GitHub Copilot CLI in
ollama launch. Added both integrations, which can now be configured in one command alongside the rest of the supported coding agents. - OpenCode moved to inline config.
ollama launch opencodenow writes its config inline rather than to a separate file, matching how other integrations are handled. ollama launchno longer rewrites config when nothing changed. Pressing → on a configured multi-model integration, or passing--modelwith the current primary, used to trigger a confirmation prompt and rewrite both the editor's config file andconfig.json. Now it's a no-op when the resolved model list matches what's already saved.- Fixed
ollama launch openclaw --yesso it correctly skips the channels configuration step, so non-interactive setups complete cleanly. - Restored the Gemma 4 nothink renderer with the e2b-style prompt.
- Fixed the Gemma 4 compiler error that was breaking Metal builds.
- Fixed macOS cross-compiles so they no longer trigger
generate, which was breaking cmake builds on some Xcode versions. - Quieted cgo builds by suppressing deprecated warnings during
go build.
Full Changelog: https://github.com/ollama/ollama/compare/v0.20.7...v0.21.0
Downloads
-
2026-04-13 18:36:51 -05:00 | 89 commits to main since this release📅 Originally published on GitHub: Tue, 14 Apr 2026 00:35:30 GMT
🏷️ Git tag created: Mon, 13 Apr 2026 23:36:51 GMTWhat's Changed
- ROCm: Update to ROCm 7.2.1 on Linux by @saman-amd in https://github.com/ollama/ollama/pull/15483
- gemma4: fix nothink case renderer by @drifkin in https://github.com/ollama/ollama/pull/15553
- gemma4: fix compiler error on metal by @dhiltgen in https://github.com/ollama/ollama/pull/15550
- gemma4: add nothink renderer tests by @drifkin in https://github.com/ollama/ollama/pull/15554
- mlx: mixed-precision quant and capability detection improvements by @dhiltgen in https://github.com/ollama/ollama/pull/15409
- mlx: add op wrappers for Conv2d, Pad, activations, trig, and masked SDPA by @dhiltgen in https://github.com/ollama/ollama/pull/14913
- Revert "gemma4: add nothink renderer tests" by @drifkin in https://github.com/ollama/ollama/pull/15555
- cgo: suppress deprecated warning to quiet down go build by @dhiltgen in https://github.com/ollama/ollama/pull/15438
- mac: prevent generate on cross-compiles by @dhiltgen in https://github.com/ollama/ollama/pull/15120
- Revert "gemma4: fix nothink case renderer" by @drifkin in https://github.com/ollama/ollama/pull/15556
- launch/opencode: use inline config by @hoyyeva in https://github.com/ollama/ollama/pull/15462
- gemma4: restore e2b-style nothink prompt by @drifkin in https://github.com/ollama/ollama/pull/15560
- Gemma4 on MLX by @dhiltgen in https://github.com/ollama/ollama/pull/15244
Full Changelog: https://github.com/ollama/ollama/compare/v0.20.6...v0.20.8-rc0
Downloads
mirror of
https://github.com/ollama/ollama.git
synced 2026-05-20 12:17:36 -05:00