unsloth v0.1.800-beta

v0.1.800-betaPre-release

Qwen3.8-27B

Added 11
  • Qwen3.8-27B and Qwen3.8-2.4T can now be run locally in Unsloth
  • Run Qwen3.8-27B on 17GB RAM via Unsloth Dynamic GGUFs
  • Fine-tune Qwen3.8-27B in Unsloth
  • NVFP4 quants for Qwen3.8-27B
  • Extra llama-server arguments can be passed through model settings in an Extra Arguments box
  • External provider has tool calling and tool support
Changed 7
  • Inference is up to 10% faster in supported cases with lower VRAM use and tunable memory limit
  • MiniMax-H3 can run on smaller supported GPUs by splitting large model parts into pieces that fit
  • Model picker hides H3 options that current hardware cannot run instead of letting them fail after selection
  • H3 options are labelled Fast FP8 or Slow to make speed difference clear before downloading
  • Chat settings stay with the conversation across remote sessions
  • Chat shows live prompt and generation speeds while long streaming replies use much less CPU
  • Macs now choose context size from memory that is actually free
Fixed 3
  • Inference speed for MiniMax-H3 is 10x faster with FP8 quantization
  • Bypass permissions fixed
  • GGUF image detection when choosing a model for the API

From unsloth

Qwen3.8-27B and Qwen3.8-2.4T can now be run locally in Unsloth! Run on 17GB RAM via Unsloth Dynamic GGUFs. You can also fine-tune Qwen3.8-27B in Unsloth. Qwen3.8-27B is by far the strongest model for its size. We also uploaded NVFP4 quants.

Guide: https://unsloth.ai/docs/models/qwen3.8 GGUF: https://huggingface.co/unsloth/Qwen3.8-27B-GGUF

See 1-bit Qwen3.8-2.4T GGUF running in Unsloth:

Highlights
  • Qwen3.8-27B + extra llama-server arguments allowed + custom VRAM toggle
  • External provider has tool calling + tool support + login with Codex
  • Fast FP8 10x faster MiniMax-H3 inference (3 minutes vs 30)
  • 10% faster inference for GGUFs + Bypass permissions fixed
Chat + tools
  • Connected AI providers can use their own Search or Unsloth Desktop's built-in Search and tools. Tool results are passed back to the model so it can continue multi-step tasks.
  • Sign in with a Codex subscription and use Codex tools inside Chat.
  • Chat shows live prompt and generation speeds, while long streaming replies use much less CPU.
  • Chat settings stay with the conversation across remote sessions.
  • Paste a YouTube link to attach its transcript, including the title, channel, duration, link, and caption language.
  • Save a full chat or reply into your project's sources while keeping its reasoning, tool calls, and citations.
MiniMax-H3
  • MiniMax-H3 can run on smaller supported GPUs by splitting large model parts into pieces that fit.
  • The model picker now hides H3 options that the current hardware cannot run instead of letting them fail after selection.
  • H3 options are labelled Fast FP8 or Slow, making the large speed difference clear before downloading.
Performance + hardware
  • Inference is up to 10% faster in supported cases, with lower VRAM use and a tunable memory limit.
  • Idle image and video models can optionally unload to free VRAM for Chat or Training.
  • Added better support for AMD RDNA 3, RDNA 4, and Strix Halo systems. VRAM checks no longer reserve extra GPU memory.
  • Multi-GPU ROCm device matching is safer.
  • Macs now choose context size from the memory that is actually free.
  • RAG document indexing uses the CPU by default, so it no longer leaves a large GPU memory block reserved.
  • Fixed GGUF image detection when choosing a model for the API.
Custom llama.cpp arguments
  • Model settings now include an Extra Arguments box for custom llama-server flags.
  • Unsloth checks flags against the installed build and saves valid ones per model for normal, startup, and API loads. Flags that could break model loading or app security are rejected with a clear message.
Training + exports
  • Training checks whether a model needs a newer Transformers version and asks before installing it. The preview also tells you when the model must use 16-bit instead of 4-bit.
  • GGUF exports check disk space before starting a long merge, with clearer errors showing how much space is needed.
  • On Kaggle, large saves can use the bigger temporary drive when the working folder is too small.
  • Fixed LoRA being ignored by vLLM GRPO rollouts on newer TRL versions.
Debugging + reliability
  • Settings > Debugging now shows the main server and model-runner logs, with live, 3-second, and manual refresh modes.
  • Copy the visible log or its full path for a bug report. Passwords, tokens, and API keys are hidden in the viewer, while files on disk stay unchanged.
  • Cached RAG models load first, avoiding long stalls when Hugging Face is unreachable.
  • Slow installs can keep running during large downloads and show what they are waiting for.
  • Fixed Hugging Face dataset links and linked folders on Windows.
  • Pinned models can be reordered by dragging them in the model list.
Download Unsloth Desktop

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

  • Windows
  • macOS
  • Linux

🦥 Download Unsloth Desktop

Star Unsloth on GitHub

What's Changed

Full Changelog: https://github.com/unslothai/unsloth/compare/v0.1.70-beta...v0.1.71-beta

View original

Upgraded? How did it go?

Discussion