Unsloth
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.
Ano ang bago
Na-verify 2h na nakalipasTurn any text or vision LLM into a Jev-style decision model in Unsloth, with decision accuracy going from 30% to 80%. Train, test, export and serve decision models directly from Unsloth. Also included: native ComfyUI models, diffusion improvements and a better Browser in Desktop.
## Highlights
- **8th Oct Fixes** - Better Browser + 100+ bug fixes + perf fixes
- **Sandboxing** with Bwrap for Linux, Seatbelt for Mac and MXC for Windows
- **Turn any model into a Jev-style decision model.** Accuracy went from 30% to 80%
- **Load ComfyUI diffusion models** natively in Unsloth
- **Faster + more accurate diffusion** with INT8 ConvRot and more
https://github.com/user-attachments/assets/92959172-d2a2-450b-a5bf-6369a1e5ae16
## Decision models
- Train any text or vision LLM as a Jev-style decision model using QLoRA.
- Test trained models directly from the Decision API settings.
- Make decisions with confidence scores for every option.
- Export Clef models with Qwen3.5 backbones and Laya models to GGUF.
- Serve supported decision models through llama.cpp, including models that understand images.
- Save and resume smaller adapter and decision-head checkpoints.
- Guide a
Buong tala ng paglabas →
## Highlights
- **8th Oct Fixes** - Better Browser + 100+ bug fixes + perf fixes
- **Sandboxing** with Bwrap for Linux, Seatbelt for Mac and MXC for Windows
- **Turn any model into a Jev-style decision model.** Accuracy went from 30% to 80%
- **Load ComfyUI diffusion models** natively in Unsloth
- **Faster + more accurate diffusion** with INT8 ConvRot and more
https://github.com/user-attachments/assets/92959172-d2a2-450b-a5bf-6369a1e5ae16
## Decision models
- Train any text or vision LLM as a Jev-style decision model using QLoRA.
- Test trained models directly from the Decision API settings.
- Make decisions with confidence scores for every option.
- Export Clef models with Qwen3.5 backbones and Laya models to GGUF.
- Serve supported decision models through llama.cpp, including models that understand images.
- Save and resume smaller adapter and decision-head checkpoints.
- Guide a
Opisyal na mga pinagmulan ng download
Ang bawat pinagmulan sa ibaba ay napatunayan laban sa aprubadong domain ng publisher at aprubado ng patnugot. Dumadaan ang mga link sa ligtas na panloob na redirect.
Na-verify na checksum Integridad ng file
Walang nakitang banta — 0/69 engine VirusTotal ↗I-verify na tumutugma ang iyong na-download na file sa opisyal na hash ng publisher bago i-install.
SHA-256
d44b3df2757906b4d7e4d1e500eec36e19f7b2cd45b86325026cf46ebeaa269d
Mga Platform: Windows
Unsloth ikinumpara
Isang makatotohanan, magkatabing pangkalahatang-ideya batay lamang sa na-verify na datos.
Mga alternatibo sa Unsloth
Na-verify, opisyal na mga download sa parehong kategorya.
Mga madalas itanong
Saan ko ligtas na mada-download ang Unsloth?
Gamitin ang mga opisyal na pinagmulan na nakalista sa pahinang ito. Ang bawat link ay napatunayan laban sa aprubadong domain ng publisher at dumaan sa ligtas na panloob na redirect — walang third-party o naka-bundle na installer.
Aling mga platform ang sinusuportahan ng Unsloth?
Ang Unsloth ay magagamit para sa Windows.
Ito ba ang opisyal na Unsloth download?
Oo. Ang bawat pinagmulan na ipinapakita dito ay napatunayan laban sa aprubadong domain ng publisher at nirepaso ng patnugot bago ilathala.
Sino ang nag-develop ng Unsloth?
Ang Unsloth ay binuo ng unslothai.
Ano ang pinakamahusay na mga alternatibo sa Unsloth?
Kabilang sa mga sikat na alternatibo ang Extract_otp_secrets, Koodo-reader at SVGShellExtensions. Tingnan ang paghahambing sa itaas para sa magkatabing pangkalahatang-ideya.
Mga pagsusuri at rating
Wala pang pagsusuri — ikaw ang unang magbahagi ng iyong karanasan.
Sumulat ng pagsusuri