# unsloth v0.1.806-beta — 2x Faster Qwen3.8-Flash + GLM-5.3-Flash MTP

- Product: unsloth (https://whatsnew.fyi/product/unsloth)
- Vendor: unslothai
- Date: 2026-09-02
- Version: v0.1.806-beta
- Original notes: https://github.com/unslothai/unsloth/releases/tag/v0.1.806-beta
- Permalink: https://whatsnew.fyi/product/unsloth/releases/v0.1.806-beta
- Labels: Pre-release

What's New is an index, not a publisher: every entry below links to the vendor's own release notes, which are the authoritative source. Entries are labelled where they are hand-curated sample data, pre-releases, or drawn from a secondary source such as a developer blog.

Reuse: the summaries, labels and curation here are © What's New. Quote freely with attribution and a link back; wholesale republication of the corpus is not permitted — terms: https://whatsnew.fyi/terms. The vendors' own release notes remain their publishers'.

---

- **added** — Enable MTP by default for Qwen3.8-Flash-Next and GLM-5.3-Flash to run up to 2x faster
- **added** — Add support for MiniMax-Music3, Higgs, and MOSS audio models
- **added** — Add live progress updates while audio is being generated
- **added** — Add local media APIs for video, audio, and MLX-served models
- **added** — Add ability to archive and manage audio clips
- **added** — Add OpenAI-compatible Videos API for video generation
- **added** — Add support for running multiple tool calls simultaneously without mixing up their arguments
- **added** — Add local code editing capability using Codex's apply_patch tool
- **added** — Add setting that tells the model the current date
- **added** — Add ability to export GLM-5.3 MLX fine-tunes to GGUF
- **added** — Add option to choose custom GGUF shard sizes and save locations
- **changed** — Enable MLX models to use their full context size and support much longer batched generation
- **changed** — Improve Qwen automatically to apply recommended settings for thinking and non-thinking modes
- **changed** — Improve multi-GPU training with automatic model placement across multiple GPUs
- **changed** — Improve AMD/ROCm detection, installation, and GPU compatibility with BF16 support on more GPUs
- **changed** — Improve MLX model loading to release GPU memory more cleanly between generation bursts and model switches
- **changed** — Improve model loading with fewer errors across local servers and connected providers
- **changed** — Improve chat safety to preserve tool cards, reply details, and conversation branches during edits
- **fixed** — Fix custom TTS playback and Whisper pairing checks for audio reliability
- **fixed** — Fix MCP connection persistence for faster tool calls within each chat

Run Qwen3.8-Flash-Next and GLM-5.3-Flash up to 2x faster with MTP. MTP is enabled by default, you can still disable it.
Also our new release includes 170+ training, chat, hardware, and performance improvements.

##### Highlights
*  **Smoother model loading** (less errors) across local servers and connected providers.
*  **Safer chat edits** that preserve tool cards, reply details, and conversation branches.
* **New local media APIs** for video, audio, and MLX-served models.
* New audio support with new models, progress tracking including: MiniMax-Music3, Higgs, MOSS and more!
* Improved multi-GPU planning, memory fitting, and split-model training.
* Strengthened AMD/ROCm detection, installation, and GPU compatibility.
* Upgraded MCP, Deep Research, OAuth, and agent tool reliability.  

##### Qwen3.8-Flash + GLM-5.3-Flash
- Qwen and GLM now generate faster with MTP enabled by default.
- Use GLM tools across longer, multi-turn chats.
- Qwen automatically applies the recommended settings for thinking and non-thinking modes.

Download [Qwen3.8-Flash-Next](https://huggingface.co/unsloth/Qwen3.8-Flash-Next) and [GLM-5.3-Flash](https://huggingface.co/unsloth/GLM-5.3-Flash). See the [Qwen guide](https://unsloth.ai/docs/models/qwen3.8-next) and [GLM guide](https://unsloth.ai/docs/models/glm-5.3-flash) for recommended settings and available GGUFs.

##### Faster MLX inference

- Fine-tune both large MoE models with text or images on Apple Silicon using MLX.
- Long Qwen chats now run much faster on Mac, with follow-up turns up to 30x faster.
- MLX models now use their full context size and support much longer batched generation.
- MLX releases GPU memory more cleanly between generation bursts and model switches.
- Serve MLX models through Unsloth's OpenAI-compatible API.

##### Audio

* Added support for **MiniMax-Music3, Higgs, MOSS audio models**. 
* Added **live progress updates** while audio is being generated. 
* Audio clips can now be **archived and managed**. 
* Improved reliability with **custom TTS playback fixes, Whisper pairing checks, and stronger audio testing**.   

##### Chat + tools

- Run several tool calls at once without mixing up their arguments.
- Keep tools available when chatting with images.
- Each chat keeps its MCP connection for faster tool calls.
- Local models can edit code using Codex’s apply_patch tool.
- Continue long chats with images and other media using Auto Compaction.
- Review and approve Deep Research plans before research starts.

##### Training + hardware

- Train larger models across multiple GPUs with automatic placement.
- AMD installs choose the best build across Windows and Linux, with BF16 on more GPUs.
- Export GLM-5.3 MLX fine-tunes to GGUF.
- Choose custom GGUF shard sizes and save locations.

##### API + Desktop

- Generate videos through the new OpenAI-compatible Videos API.
- Updates download in the background and install when you restart.
- Choose a custom port for LAN access.
- Generate audio with Higgs, MOSS and MiniMax models.
- Track audio generation progress and archive finished clips.
- Model downloads show clearer progress and can switch from Xet to HTTP automatically.

##### Download Unsloth Desktop

Unsloth Desktop is **free and open source**. Download it for:

- **Windows**
- **macOS**
- **Linux**

**[🦥 Download Unsloth Desktop](https://unsloth.ai/download)**

##### What's Changed
* Put the smart offload planner back behind its flag by @danielhanchen in https://github.com/unslothai/unsloth/pull/9862
* Studio: stop the per-chunk autosave writing back messages the server owns by @danielhanchen in https://github.com/unslothai/unsloth/pull/9865
* Bump install.sh / install.ps1 pins to unsloth>=2026.8.22 by @danielhanchen in https://github.com/unslothai/unsloth/pull/9868
* Fix Studio hydrating synced GGUF files before selection by @milewski in https://github.com/unslothai/unsloth/pull/9539
* Fix datasets PyA

_[Truncated at 4000 characters — full notes: https://github.com/unslothai/unsloth/releases/tag/v0.1.806-beta]_