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 baharu
Disahkan 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
Nota keluaran penuh →
## 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 muat turun rasmi
Setiap sumber di bawah telah disahkan terhadap domain penerbit yang diluluskan dan diluluskan secara editorial. Pautan dihalakan melalui pengalihan semula dalaman yang selamat.
Checksum disahkan Integriti fail
Tiada ancaman dikesan — 0/69 enjin VirusTotal ↗Sahkan fail yang dimuat turun sepadan dengan hash rasmi penerbit sebelum pemasangan.
SHA-256
d44b3df2757906b4d7e4d1e500eec36e19f7b2cd45b86325026cf46ebeaa269d
Platform: Windows
Unsloth dibandingkan
Gambaran keseluruhan bersebelahan berdasarkan fakta daripada data yang disahkan sahaja.
| Atribut | Unsloth Halaman ini | eSearch | LXD | AI Disk Cleaner |
|---|---|---|---|---|
| Pembangun | unslothai | xushengfeng | Canonical | vudsen |
| Kategori | Utilities | Utilities | Utilities | Utilities |
| Platform | Windows | Windows | Windows | Windows |
| Sumber rasmi | 1 | 1 | 1 | 1 |
| Rasmi disahkan | ✓ | ✓ | ✓ | ✓ |
Alternatif kepada Unsloth
Muat turun rasmi yang disahkan dalam kategori yang sama.
Soalan lazim
Di mana saya boleh memuat turun Unsloth dengan selamat?
Gunakan sumber rasmi yang tersenarai di halaman ini. Setiap pautan disahkan terhadap domain penerbit yang diluluskan dan dihalakan melalui pengalihan semula dalaman yang selamat — tiada pemasang pihak ketiga atau bungkusan.
Platform mana yang disokong oleh Unsloth?
Unsloth tersedia untuk Windows.
Adakah ini muat turun rasmi Unsloth?
Ya. Setiap sumber yang ditunjukkan di sini disahkan terhadap domain penerbit yang diluluskan dan disemak secara editorial sebelum diterbitkan.
Siapa yang membangunkan Unsloth?
Unsloth dibangunkan oleh unslothai.
Apakah alternatif terbaik kepada Unsloth?
Alternatif popular termasuk Beyondtranslate-ce, Bombardier dan File-transfer-go. Lihat perbandingan di atas untuk gambaran bersebelahan.
Ulasan & penilaian
Tiada ulasan lagi — jadilah yang pertama untuk berkongsi pengalaman anda.
Tulis ulasan