-
GiteaMirror released this
2025-03-17 17:41:37 -05:00 | 772 commits to main since this release📅 Originally published on GitHub: Tue, 18 Mar 2025 03:11:33 GMT
🏷️ Git tag created: Mon, 17 Mar 2025 22:41:37 GMTWhat's Changed
- Multiple images are now supported in Gemma 3
- Fixed issue where running Gemma 3 would consume a large amount of system memory
ollama create --quantizenow works when converting Gemma 3 from safetensors- Fixed issue where
/savewould not work if running a model with/in the name - Add support for AMD Strix Halo GPUs
New Contributors
- @zeozeozeo made their first contribution in https://github.com/ollama/ollama/pull/9800
- @louis030195 made their first contribution in https://github.com/ollama/ollama/pull/9786
Full Changelog: https://github.com/ollama/ollama/compare/v0.6.1...v0.6.2
Downloads
-
2025-03-14 10:57:59 -05:00 | 789 commits to main since this release📅 Originally published on GitHub: Fri, 14 Mar 2025 02:58:48 GMT
🏷️ Git tag created: Fri, 14 Mar 2025 15:57:59 GMTNew models
- Command A: 111 billion parameter model optimized for demanding enterprises that require fast, secure, and high-quality AI.
What's Changed
- Fixed issues where
gemma3would crash with "out of memory (OOM)" errors by improving memory estimation - Loading an invalid model with
/loadwill no longer exitollama run - Added Ctrl+P and Ctrl+N hotkeys for
ollama run - New
ollama show -vorollama show --verbosethat will print additional model data - Improved sampling parameters such as
temperatureandtop_kto behave similar to other implementations
New Contributors
- @Shane-XB-Qian made their first contribution in https://github.com/ollama/ollama/pull/9136
- @13rac1 made their first contribution in https://github.com/ollama/ollama/pull/9643
Full Changelog: https://github.com/ollama/ollama/compare/v0.6.0...v0.6.1
Downloads
-
2025-03-11 17:07:50 -05:00 | 816 commits to main since this release📅 Originally published on GitHub: Tue, 11 Mar 2025 23:37:42 GMT
🏷️ Git tag created: Tue, 11 Mar 2025 22:07:50 GMTNew Model
- Gemma 3: Google Gemma 3 model is now available in 1B, 4B, 12B, and 27B parameter sizes.
What's Changed
- Fixed error that would occur when running
snowflake-arctic-embedandsnowflake-arctic-embed2models
New Contributors
- @iBreaker made their first contribution in https://github.com/ollama/ollama/pull/9565
- @zhu-xiaowei made their first contribution in https://github.com/ollama/ollama/pull/9540
- @dwt made their first contribution in https://github.com/ollama/ollama/pull/9569
- @vincentkoc made their first contribution in https://github.com/ollama/ollama/pull/9626
Full Changelog: https://github.com/ollama/ollama/compare/v0.5.13...v0.6.0
Downloads
-
2025-03-03 21:11:16 -06:00 | 890 commits to main since this release📅 Originally published on GitHub: Thu, 27 Feb 2025 18:27:51 GMT
🏷️ Git tag created: Tue, 04 Mar 2025 03:11:16 GMTNew models
- Phi-4-Mini: Phi-4-mini brings significant enhancements in multilingual support, reasoning, and mathematics, and now, the long-awaited function calling feature is finally supported.
- Granite-3.2-Vision: A compact and efficient vision-language model, specifically designed for visual document understanding, enabling automated content extraction from tables, charts, infographics, plots, diagrams, and more.
- Command R7B Arabic: A new state-of-the-art version of the lightweight Command R7B model that excels in advanced Arabic language capabilities for enterprises in the Middle East and Northern Africa.
What's Changed
- The default context length can now be set with a new
OLLAMA_CONTEXT_LENGTHenvironment variable. For example, to set the default context length to 8K, use:OLLAMA_CONTEXT_LENGTH=8192 ollama serve - Ollama is now compiled for NVIDIA Blackwell
- Fixed issue where bf16 GGUF files could not be imported
- Ollama is now be able to accept requests from Visual Studio Code and Cursor by accepting requests from origins beginning with
vscode-file:// - Fixed a series of
permission deniedissues when installing Ollama on Linux
Note: Ubuntu 20.04, Debian 10 and RHEL 8+ or later are required to run Ollama on Linux
New Contributors
- @prusnak made their first contribution in https://github.com/ollama/ollama/pull/8567
- @ChuanhuiLiu made their first contribution in https://github.com/ollama/ollama/pull/9346
- @Pekkari made their first contribution in https://github.com/ollama/ollama/pull/8211
- @eriestrisnadi made their first contribution in https://github.com/ollama/ollama/pull/9313
- @stevenh made their first contribution in https://github.com/ollama/ollama/pull/9360
- @wanghe-fit2cloud made their first contribution in https://github.com/ollama/ollama/pull/9312
- @Soulter made their first contribution in https://github.com/ollama/ollama/pull/9442
- @ibrahimcetin made their first contribution in https://github.com/ollama/ollama/pull/9411
- @remarkablemark made their first contribution in https://github.com/ollama/ollama/pull/9456
- @googs1025 made their first contribution in https://github.com/ollama/ollama/pull/9458
- @sunshine0523 made their first contribution in https://github.com/ollama/ollama/pull/9468
Full Changelog: https://github.com/ollama/ollama/compare/v0.5.12...v0.5.13
Downloads
-
2025-02-23 21:13:53 -06:00 | 950 commits to main since this release📅 Originally published on GitHub: Thu, 20 Feb 2025 17:32:40 GMT
🏷️ Git tag created: Mon, 24 Feb 2025 03:13:53 GMTNew models
- Perplexity R1 1776: A version of the DeepSeek-R1 model that has been post trained to remove its refusal to respond to some sensitive topics.
What's Changed
- The OpenAI-compatible API will now return
tool_callsif the model called a tool - Performance on certain Intel Xeon processors should now be restored
- Fixed permission denied issues after installing Ollama on Linux
- Fixed issue where additional CPU libraries were included in the
arm64Linux install - The progress bar will no longer flicker when running
ollama pull - Fixed issue where running a model would fail on Linux if Ollama was installed in a path with UTF-8 characters
X-Stainless-Timeoutwill now be accepted as a header in the OpenAI API endpoints
New Contributors
- @buiducnhat made their first contribution in https://github.com/ollama/ollama/pull/9075
- @James-William-Kincaid-III made their first contribution in https://github.com/ollama/ollama/pull/9098
- @innightwolfsleep made their first contribution in https://github.com/ollama/ollama/pull/9150
- @ismdeep made their first contribution in https://github.com/ollama/ollama/pull/9108
- @benhaotang made their first contribution in https://github.com/ollama/ollama/pull/9138
- @jeremyschlatter made their first contribution in https://github.com/ollama/ollama/pull/9079
- @maninhill made their first contribution in https://github.com/ollama/ollama/pull/9212
- @xuzeyu91 made their first contribution in https://github.com/ollama/ollama/pull/9214
- @yuiseki made their first contribution in https://github.com/ollama/ollama/pull/9146
- @lucasthahn made their first contribution in https://github.com/ollama/ollama/pull/9237
- @danielekp made their first contribution in https://github.com/ollama/ollama/pull/9251
- @RockChinQ made their first contribution in https://github.com/ollama/ollama/pull/9272
Full Changelog: https://github.com/ollama/ollama/compare/v0.5.11...v0.5.12
Downloads
-
2025-02-14 00:38:23 -06:00 | 1000 commits to main since this release📅 Originally published on GitHub: Fri, 14 Feb 2025 08:25:18 GMT
🏷️ Git tag created: Fri, 14 Feb 2025 06:38:23 GMTWhat's Changed
- Fixed
The system cannot find the path specifiederrors when running models in some cases on Windows - Fixed issue where running
ollama serveon Intel Macs would not use CPU acceleration
Full Changelog: https://github.com/ollama/ollama/compare/v0.5.10...v0.5.11
Downloads
- Fixed
-
2025-02-13 20:43:33 -06:00 | 1002 commits to main since this release📅 Originally published on GitHub: Fri, 14 Feb 2025 04:14:34 GMT
🏷️ Git tag created: Fri, 14 Feb 2025 02:43:33 GMTWhat's Changed
- Fixed issue on multi-GPU Windows and Linux machines where memory estimations would be incorrect
Full Changelog: https://github.com/ollama/ollama/compare/v0.5.9...v0.5.10
Downloads
-
2025-02-13 02:23:17 -06:00 | 1003 commits to main since this release📅 Originally published on GitHub: Wed, 12 Feb 2025 02:33:49 GMT
🏷️ Git tag created: Thu, 13 Feb 2025 08:23:17 GMTNew models
- DeepScaleR: A fine-tuned version of Deepseek-R1-Distilled-Qwen-1.5B that surpasses the performance of OpenAI’s o1-preview with just 1.5B parameters on popular math evaluations.
- OpenThinker: A fully open-source family of reasoning models built using a dataset derived by distilling DeepSeek-R1.
What's Changed
- Fixed
llama runner process has terminatedthat would occur on Windows due to permissions issues
Full Changelog: https://github.com/ollama/ollama/compare/v0.5.8...v0.5.9
Downloads
-
2025-02-10 11:52:12 -06:00 | 1009 commits to main since this release📅 Originally published on GitHub: Wed, 05 Feb 2025 20:40:08 GMT
🏷️ Git tag created: Mon, 10 Feb 2025 17:52:12 GMTWhat's Changed
- Ollama will now use AVX-512 instructions where available for additional CPU acceleration
- NVIDIA and AMD GPUs can now be used with CPUs without AVX instructions
- Ollama will now use AVX2 instructions with NVIDIA and AMD GPUs
- New
ollama-darwin.tgzpackage for macOS that replaces the previousollama-darwinstandalone binary. - Fixed indexing error that would occur when downloading a model with
ollama runorollama pull - Fixes cases where download progress would reverse
Note
The steps to build Ollama with GPU acceleration from source have changed. Please see the development documentation for more information.
New Contributors
- @jannikmaierhoefer made their first contribution in https://github.com/ollama/ollama/pull/8455
- @EndoTheDev made their first contribution in https://github.com/ollama/ollama/pull/8487
- @danielpunkass made their first contribution in https://github.com/ollama/ollama/pull/8524
- @lofcz made their first contribution in https://github.com/ollama/ollama/pull/8551
- @XiaofuHuang made their first contribution in https://github.com/ollama/ollama/pull/8604
- @anilkay made their first contribution in https://github.com/ollama/ollama/pull/8767
- @Bert0ns made their first contribution in https://github.com/ollama/ollama/pull/8766
- @melroy89 made their first contribution in https://github.com/ollama/ollama/pull/8802
- @TilmanGriesel made their first contribution in https://github.com/ollama/ollama/pull/8803
- @fallenreaper made their first contribution in https://github.com/ollama/ollama/pull/8746
- @yashwanth2706 made their first contribution in https://github.com/ollama/ollama/pull/8831
- @fyvri made their first contribution in https://github.com/ollama/ollama/pull/8692
- @daniellok-db made their first contribution in https://github.com/ollama/ollama/pull/8811
- @dpereira made their first contribution in https://github.com/ollama/ollama/pull/8714
- @zyphixor made their first contribution in https://github.com/ollama/ollama/pull/8659
- @abhitrueprogrammer made their first contribution in https://github.com/ollama/ollama/pull/8897
- @oslook made their first contribution in https://github.com/ollama/ollama/pull/8084
- @CosmicEventHorizon made their first contribution in https://github.com/ollama/ollama/pull/8883
- @annilq made their first contribution in https://github.com/ollama/ollama/pull/8877
- @LeisureLinux made their first contribution in https://github.com/ollama/ollama/pull/8905
- @kontactguddu made their first contribution in https://github.com/ollama/ollama/pull/8603
- @dravenk made their first contribution in https://github.com/ollama/ollama/pull/8688
- @qusaismael made their first contribution in https://github.com/ollama/ollama/pull/8953
- @hughcrt made their first contribution in https://github.com/ollama/ollama/pull/8975
Full Changelog: https://github.com/ollama/ollama/compare/v0.5.7...v0.5.8
Downloads
-
2025-01-16 03:14:04 -06:00 | 1065 commits to main since this release📅 Originally published on GitHub: Thu, 16 Jan 2025 18:17:33 GMT
🏷️ Git tag created: Thu, 16 Jan 2025 09:14:04 GMTWhat's Changed
- Fixed issue where using two
FROMcommands inModelfile - Support importing Command R and Command R+ architectures from safetensors
New Contributors
- @Gloryjaw made their first contribution in https://github.com/ollama/ollama/pull/8438
Full Changelog: https://github.com/ollama/ollama/compare/v0.5.6...v0.5.7
Downloads
- Fixed issue where using two
mirror of
https://github.com/ollama/ollama.git
synced 2025-12-05 18:46:22 -06:00