1. A Chat UI which has auto healing tool calling, Python & bash code execution, web search, image, docs input + more!
2. Finetuning of audio, vision, LLMs with an Auto AI Assist data prep
3. Supports GGUFs, Mac, Windows, Linux + audio gen
4. Has SVG rendering in browser, exporting to GGUF
5. gpt-oss harmony rendering, all inference parameters are pre-set and recommended
6. Data designer + synthetic data generation
7. Fast parallel data prep + embedding finetuning
8. And much much more!
To get it, run:
pip install unsloth
unsloth studio setup
unsloth studio -H 0.0.0.0 -p 8888
Suggestions are welcome, and we're excited for contributions and for you all to try it out! Appreciate you all!"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["unsloth"],"value":"Show HN: Unsloth Studio - Local Fine-tuning, Chat UI"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["unsloth"],"value":"https://github.com/unslothai/unsloth"}},"_tags":["story","author_danielhanchen","story_47414372","show_hn"],"author":"danielhanchen","children":[47415171,47417925],"created_at":"2026-03-17T15:50:58Z","created_at_i":1773762658,"num_comments":2,"objectID":"47414372","points":8,"story_id":47414372,"story_text":"Hey HN! We're excited to release Unsloth Studio - a culmination of many things we wanted to provide to the community - it includes:
1. A Chat UI which has auto healing tool calling, Python & bash code execution, web search, image, docs input + more!
2. Finetuning of audio, vision, LLMs with an Auto AI Assist data prep
3. Supports GGUFs, Mac, Windows, Linux + audio gen
4. Has SVG rendering in browser, exporting to GGUF
5. gpt-oss harmony rendering, all inference parameters are pre-set and recommended
6. Data designer + synthetic data generation
7. Fast parallel data prep + embedding finetuning
8. And much much more!
To get it, run:
pip install unsloth
unsloth studio setup
unsloth studio -H 0.0.0.0 -p 8888
Suggestions are welcome, and we're excited for contributions and for you all to try it out! Appreciate you all!","title":"Show HN: Unsloth Studio - Local Fine-tuning, Chat UI","updated_at":"2026-03-20T21:43:11Z","url":"https://github.com/unslothai/unsloth"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"handfuloflight"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["unsloth"],"value":"Run Qwen3-Coder-480B-A35B Locally with Unsloth Dynamic Quants"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["unsloth"],"value":"https://docs.unsloth.ai/basics/qwen3-coder"}},"_tags":["story","author_handfuloflight","story_44655097"],"author":"handfuloflight","created_at":"2025-07-23T02:09:37Z","created_at_i":1753236577,"num_comments":0,"objectID":"44655097","points":8,"story_id":44655097,"title":"Run Qwen3-Coder-480B-A35B Locally with Unsloth Dynamic Quants","updated_at":"2025-07-23T11:09:12Z","url":"https://docs.unsloth.ai/basics/qwen3-coder"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"mohsen1"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["unsloth"],"value":"Train your own R1 reasoning model with Unsloth"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["unsloth"],"value":"https://unsloth.ai/blog/r1-reasoning"}},"_tags":["story","author_mohsen1","story_42969736"],"author":"mohsen1","created_at":"2025-02-07T05:32:16Z","created_at_i":1738906336,"num_comments":0,"objectID":"42969736","points":6,"story_id":42969736,"title":"Train your own R1 reasoning model with Unsloth","updated_at":"2025-03-29T12:34:20Z","url":"https://unsloth.ai/blog/r1-reasoning"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"ZQ-Dev8"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["unsloth"],"value":"Unsloth creators fix universal error with gradient accumulation"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["unsloth"],"value":"https://unsloth.ai/blog/gradient"}},"_tags":["story","author_ZQ-Dev8","story_41864504"],"author":"ZQ-Dev8","children":[41864511,41864915],"created_at":"2024-10-16T22:30:47Z","created_at_i":1729117847,"num_comments":2,"objectID":"41864504","points":4,"story_id":41864504,"title":"Unsloth creators fix universal error with gradient accumulation","updated_at":"2024-10-19T03:23:46Z","url":"https://unsloth.ai/blog/gradient"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"theanonymousone"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["unsloth"],"value":"Microsoft forms partnership with Unsloth AI about local LLM execution"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["unsloth"],"value":"https://xcancel.com/UnslothAI/status/2061925637892297122"}},"_tags":["story","author_theanonymousone","story_48381283"],"author":"theanonymousone","children":[48381494],"created_at":"2026-06-03T08:10:12Z","created_at_i":1780474212,"num_comments":0,"objectID":"48381283","points":4,"story_id":48381283,"title":"Microsoft forms partnership with Unsloth AI about local LLM execution","updated_at":"2026-06-05T14:17:12Z","url":"https://xcancel.com/UnslothAI/status/2061925637892297122"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"tosh"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["unsloth"],"value":"Unsloth: GLM-4.7-Flash"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["unsloth"],"value":"https://unsloth.ai/docs/models/glm-4.7-flash"}},"_tags":["story","author_tosh","story_46691840"],"author":"tosh","created_at":"2026-01-20T13:51:48Z","created_at_i":1768917108,"num_comments":0,"objectID":"46691840","points":4,"story_id":46691840,"title":"Unsloth: GLM-4.7-Flash","updated_at":"2026-03-05T23:28:58Z","url":"https://unsloth.ai/docs/models/glm-4.7-flash"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"electroglyph"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["unsloth"],"value":"1.8-3.3x faster Embedding finetuning now in Unsloth"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["unsloth"],"value":"https://unsloth.ai/docs/new/embedding-finetuning"}},"_tags":["story","author_electroglyph","story_46726449"],"author":"electroglyph","children":[46726450,46726516,46731793],"created_at":"2026-01-22T23:26:08Z","created_at_i":1769124368,"num_comments":3,"objectID":"46726449","points":3,"story_id":46726449,"title":"1.8-3.3x faster Embedding finetuning now in Unsloth","updated_at":"2026-03-05T23:23:43Z","url":"https://unsloth.ai/docs/new/embedding-finetuning"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"timmyd"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["unsloth"],"value":"How to Beat Unsloth's CUDA Kernel Using Mojo\u2013With Zero GPU Experience"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["unsloth"],"value":"https://www.modular.com/blog/how-to-beat-unsloth-s-cuda-kernel-using-mojo-with-zero-gpu-experience"}},"_tags":["story","author_timmyd","story_46619517"],"author":"timmyd","children":[46619518],"created_at":"2026-01-14T17:56:46Z","created_at_i":1768413406,"num_comments":1,"objectID":"46619517","points":3,"story_id":46619517,"title":"How to Beat Unsloth's CUDA Kernel Using Mojo\u2013With Zero GPU Experience","updated_at":"2026-03-05T23:24:00Z","url":"https://www.modular.com/blog/how-to-beat-unsloth-s-cuda-kernel-using-mojo-with-zero-gpu-experience"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"ericcurtin"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["unsloth"],"value":"We've been working with Docker to make running quantized models easier with Docker. This integration allows users to pull and run Unsloth-optimized models using the native Docker CLI.
Key features:
Uses docker model run syntax.
Supports Dynamic GGUFs (handling quantization overhead).
Cross-platform support.
Example usage: docker model run ai/gpt-oss:20B
Happy to answer questions about the implementation or the quantization methods used.
https://docs.unsloth.ai/models/how-to-run-llms-with-docker"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["unsloth"],"value":"Show HN: Run Unsloth Dynamic GGUFs using Docker model runner"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/docker/model-runner"}},"_tags":["story","author_ericcurtin","story_45983470","show_hn"],"author":"ericcurtin","children":[45983724],"created_at":"2025-11-19T18:52:52Z","created_at_i":1763578372,"num_comments":1,"objectID":"45983470","points":3,"story_id":45983470,"story_text":"We've been working with Docker to make running quantized models easier with Docker. This integration allows users to pull and run Unsloth-optimized models using the native Docker CLI.
Key features:
Uses docker model run syntax.
Supports Dynamic GGUFs (handling quantization overhead).
Cross-platform support.
Example usage: docker model run ai/gpt-oss:20B
Happy to answer questions about the implementation or the quantization methods used.
https://docs.unsloth.ai/models/how-to-run-llms-with-docker","title":"Show HN: Run Unsloth Dynamic GGUFs using Docker model runner","updated_at":"2026-03-05T23:03:07Z","url":"https://github.com/docker/model-runner"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"Tomte"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["unsloth"],"value":"Unsloth: 30x faster AI training"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["unsloth"],"value":"https://unsloth.ai/introducing"}},"_tags":["story","author_Tomte","story_38488966"],"author":"Tomte","children":[38496750],"created_at":"2023-12-01T16:55:52Z","created_at_i":1701449752,"num_comments":1,"objectID":"38488966","points":3,"story_id":38488966,"title":"Unsloth: 30x faster AI training","updated_at":"2024-09-20T15:52:54Z","url":"https://unsloth.ai/introducing"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"jhack"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["unsloth"],"value":"Unsloth \u2013 Train LLMs 2x faster with 70% less VRAM"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["unsloth"],"value":"https://github.com/unslothai/unsloth"}},"_tags":["story","author_jhack","story_46220748"],"author":"jhack","created_at":"2025-12-10T17:38:23Z","created_at_i":1765388303,"num_comments":0,"objectID":"46220748","points":3,"story_id":46220748,"title":"Unsloth \u2013 Train LLMs 2x faster with 70% less VRAM","updated_at":"2026-03-05T23:08:30Z","url":"https://github.com/unslothai/unsloth"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"frainfreeze"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["unsloth"],"value":"Unsloth Dynamic GGUFs DeepSeek (671B) outperforms SOTA models"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["unsloth"],"value":"https://docs.unsloth.ai/basics/unsloth-dynamic-ggufs-on-aider-polyglot"}},"_tags":["story","author_frainfreeze","story_45200979"],"author":"frainfreeze","created_at":"2025-09-10T17:30:06Z","created_at_i":1757525406,"num_comments":0,"objectID":"45200979","points":3,"story_id":45200979,"title":"Unsloth Dynamic GGUFs DeepSeek (671B) outperforms SOTA models","updated_at":"2026-03-05T22:37:51Z","url":"https://docs.unsloth.ai/basics/unsloth-dynamic-ggufs-on-aider-polyglot"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"serialx"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["unsloth"],"value":"Unsloth Dynamic 2.0 GGUFs"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["unsloth"],"value":"https://docs.unsloth.ai/basics/unsloth-dynamic-2.0-ggufs"}},"_tags":["story","author_serialx","story_44698237"],"author":"serialx","created_at":"2025-07-27T01:43:30Z","created_at_i":1753580610,"num_comments":0,"objectID":"44698237","points":3,"story_id":44698237,"title":"Unsloth Dynamic 2.0 GGUFs","updated_at":"2025-07-27T20:00:45Z","url":"https://docs.unsloth.ai/basics/unsloth-dynamic-2.0-ggufs"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"sadiq"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["unsloth"],"value":"Unsloth Now Supports GRPO"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["unsloth"],"value":"https://github.com/unslothai/unsloth/releases/tag/2025-02"}},"_tags":["story","author_sadiq","story_42965893"],"author":"sadiq","children":[42965895],"created_at":"2025-02-06T19:55:37Z","created_at_i":1738871737,"num_comments":0,"objectID":"42965893","points":3,"story_id":42965893,"title":"Unsloth Now Supports GRPO","updated_at":"2025-02-07T00:43:44Z","url":"https://github.com/unslothai/unsloth/releases/tag/2025-02"}],"hitsPerPage":20,"nbHits":7101,"nbPages":50,"page":0,"params":"query=unsloth&advancedSyntax=true&analyticsTags=backend","processingTimeMS":9,"processingTimingsMS":{"_request":{"roundTrip":15},"fetch":{"query":6,"scanning":1,"total":8},"total":9},"query":"unsloth","serverTimeMS":9}