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.
Apa yang baru
Diverifikasi 1h yang laluTurn 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
Catatan rilis lengkap →
## 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
Sumber unduhan resmi
Setiap sumber di bawah ini telah divalidasi terhadap domain penerbit yang disetujui dan disetujui secara editorial. Tautan dialihkan melalui pengalihan internal yang aman.
Checksum terverifikasi Integritas file
Tidak ada ancaman terdeteksi — 0/69 mesin VirusTotal ↗Verifikasi bahwa file yang diunduh cocok dengan hash resmi penerbit sebelum menginstal.
SHA-256
d44b3df2757906b4d7e4d1e500eec36e19f7b2cd45b86325026cf46ebeaa269d
Platform: Windows
Unsloth dibandingkan
Ikhtisar berdampingan faktual hanya berdasarkan data terverifikasi.
| Atribut | Unsloth Halaman ini | Clash Verge Rev | GPXSee | Comic-book-reader |
|---|---|---|---|---|
| Pengembang | unslothai | GyDi | Martin Tůma | binarynonsense |
| Kategori | Utilities | Utilities | Utilities | Utilities |
| Platform | Windows | Windows | Windows | Windows |
| Sumber resmi | 1 | 1 | 1 | 1 |
| Resmi terverifikasi | ✓ | ✓ | ✓ | ✓ |
Alternatif untuk Unsloth
Unduhan resmi terverifikasi dalam kategori yang sama.
Pertanyaan yang sering diajukan
Di mana saya dapat mengunduh Unsloth dengan aman?
Gunakan sumber resmi yang tercantum di halaman ini. Setiap tautan divalidasi terhadap domain penerbit yang disetujui dan dialihkan melalui pengalihan internal yang aman — tidak ada penginstal pihak ketiga atau bundel.
Platform apa yang didukung Unsloth?
Unsloth tersedia untuk Windows.
Apakah ini unduhan resmi Unsloth?
Ya. Setiap sumber yang ditampilkan di sini divalidasi terhadap domain penerbit yang disetujui dan ditinjau secara editorial sebelum diterbitkan.
Siapa yang mengembangkan Unsloth?
Unsloth dikembangkan oleh unslothai.
Apa alternatif terbaik untuk Unsloth?
Alternatif populer meliputi yt-dlp, Spacedrive dan OpenIoTHub. Lihat perbandingan di atas untuk ikhtisar berdampingan.
Ulasan & penilaian
Belum ada ulasan — jadilah yang pertama berbagi pengalaman.
Tulis ulasan