unsloth

AI

Local UI to run and train LLMs and diffusion models, including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, FLUX and more.

Latest v0.1.804-beta · by unslothaiWebsiteunslothai/unslothRSS

Release activity

Release activity — 10 releases across 7 days since Aug 10, 2026. Each cell is one day; darker means more releases that day. Nothing is recorded before Aug 10, 2026. Older weeks are hidden at this screen width.
JunJulAug
SundayNo releases on Aug 16, 2026No releases on Aug 23, 2026No releases on Aug 30, 2026
Monday1 release on Aug 10, 2026No releases on Aug 17, 2026No releases on Aug 24, 2026
Tuesday3 releases on Aug 11, 2026No releases on Aug 18, 20262 releases on Aug 25, 2026
WednesdayNo releases on Aug 12, 2026No releases on Aug 19, 2026No releases on Aug 26, 2026
Thursday1 release on Aug 13, 20261 release on Aug 20, 20261 release on Aug 27, 2026
Friday1 release on Aug 14, 2026No releases on Aug 21, 2026No releases on Aug 28, 2026
SaturdayNo releases on Aug 15, 2026No releases on Aug 22, 2026No releases on Aug 29, 2026

10 releases since Aug 10, 2026, busiest day 3

Changelog

v0.1.804-betaPre-release

Qwen3.8-Flash-Next + GLM-5.3-Flash

Added 5
  • Support for running Qwen3.8-Flash-Next locally on 75GB RAM
  • Support for running GLM-5.3-Flash locally on 102GB total RAM and VRAM
  • Local chats resume after a disconnect instead of losing the reply
  • Export chats as JSONL for backups or use in other tools
  • Search and download embedding models directly from Hugging Face
Changed 9
  • Inference speed improved 5x for RAM offloading
  • Large GGUFs automatically split across GPU and system RAM
  • Smarter GPU and RAM offloading to run larger models with less setup
  • Vision chats now handle multiple images properly
  • Text-to-speech models only load when actually used
  • Model settings stay saved when switching chats
Fixed 6
  • Infinite repeated compaction now works
  • Linux voice recording fixed
  • NVIDIA and Wayland interface freezes fixed
  • AMD model loading crashes fixed
  • llama.cpp models now load from Windows profiles with non-English characters
  • Non-English web links now work properly as chat sources

From unsloth

Qwen3.8-Flash-Next and GLM-5.3-Flash can now run locally in Unsloth!

  • Run Qwen3.8-Flash on 75GB RAM, GLM-5.3-Flash on 102GB RAM+VRAM
  • 5x Faster inference for RAM offloading
  • "Infinite" repeated compaction now works
  • 100+ chat, reliability and performance improvements

Qwen Guide: https://unsloth.ai/docs/models/qwen3.8-next
Qwen GGUFs: https://huggingface.co/unsloth/Qwen3.8-Flash-Next-GGUF
GLM Guide: https://unsloth.ai/docs/models/glm-5.3-flash
GLM GGUFs: https://huggingface.co/unsloth/GLM-5.3-Flash-GGUF

Highlights
  • Qwen3.8-Flash-Next on 75GB RAM
  • GLM-5.3-Flash on 102GB total memory
  • Smarter GPU + RAM offloading - run larger models with less setup
  • Chats recover after disconnects instead of losing the reply
  • See what fits before loading with clearer memory estimates
Qwen3.8-Flash-Next

Qwen3.8-Flash-Next is a new 125B multimodal reasoning model and an early preview of Qwen4's architecture.

  • The 1-bit Unsloth Dynamic GGUF runs on 75GB RAM or unified memory.
  • It's 79% smaller than BF16 while retaining 80% top-1 accuracy.
  • Chat with text and images using up to 262K context.
  • Switch between None, Low, Medium and Extra High reasoning.
  • Preserved Thinking keeps reasoning consistent across longer chats.
GLM-5.3-Flash

GLM-5.3-Flash is Z.ai's new 320B multimodal model, with only 18B parameters active at a time.

  • Run the 1-bit model on 102GB of combined RAM + VRAM.
  • Chat with text, images and long documents using up to 1M context.
  • Switch between Low, High and Max reasoning.
  • Stronger coding, agent and vision performance than GLM-5.2.
  • Recommended settings are applied automatically in Unsloth.
Chat + tools
  • Local chats resume after a disconnect instead of losing the reply.
  • Deep Research keeps going when a provider asks it to slow down.
  • Vision chats now handle multiple images properly.
  • Images returned by MCP tools appear directly in chat.
  • Export chats as JSONL for backups or use in other tools.
  • Adjust Auto Compaction for longer chats, or turn it off.
  • Collapse tool activity by default for cleaner agent chats.
Models + performance
  • Large GGUFs automatically split across GPU and system RAM.
  • See estimated memory usage before loading a model.
  • View VRAM usage directly from your downloaded models.
  • Model settings stay saved when switching chats.
  • Search and download embedding models directly from Hugging Face.
  • Text-to-speech models only load when you actually use them.
Desktop + reliability
  • Linux voice recording fixed.
  • NVIDIA + Wayland interface freezes fixed.
  • AMD model loading crashes fixed.
  • llama.cpp models now load from Windows profiles with non-English characters.
  • Non-English web links now work properly as chat sources.
  • Desktop download links always point to the latest stable release.
What's Changed
New Contributors

Full Changelog: https://github.com/unslothai/unsloth/compare/v0.1.803-beta...v0.1.804-beta

View originalPermalink
How v0.1.804-beta went
v0.1.803-betaPre-release

Bug Fixes + Auto compaction + LAN Remote Access

Added 10
  • Added LAN API keyless and password-less access with keyboard shortcuts
  • Added XET and HTTP download toggle for clearer download progress
  • Added Auto Compaction (Experimental) for longer chats beyond context limits
  • Added Remote and LAN Access (Preview) for easy network access without Cloudflare links
  • Added support for custom llama.cpp builds with toggles for Cache RAM, Mmap, Mlock, Checkpoints, Speculative Decoding KV Cache, and Vision On/Off
  • Released Unsloth Dynamic v3.0 with Qwen3.8-27B GGUFs delivering over 10% higher top-1 accuracy
Changed 8
  • Improved chat streaming performance, reduced UI lag, and made long conversations smoother
  • Improved tool calling and MCP behavior
  • Responses API now supports structured output formatting
  • Improved recovery when llama-server crashes
  • Improved GGUF downloads to be faster
  • Improved Desktop packaging and permissions
  • Improved training scheduler and preprocessing
  • Improved compatibility across ROCm, xFormers, and flash-attention setups
Fixed 2
  • Fixed MLX and Mac runtimes that did not run correctly
  • Fixed AMD bugs and 170 bug, reliability, and performance issues

From unsloth

Thanks for the support for Qwen3.8-27B and Unsloth Desktop! This is a bug fix release with 170+ PRs.

  • MLX fixed - Some MLX and Mac runtimes did not run correctly
  • LAN API keyless / password-less + Keyboard shortcuts
  • XET / HTTP download toggle - clearer download progress
  • AMD bug fixes + 170 bug, reliability & performance fixes
Features
  • Auto Compaction (Experimental) for longer chats beyond context limits
  • Remote & LAN Access (Preview) for easy network access without Cloudflare links
  • Faster Chat - Improved streaming performance, reduced UI lag, and smoother long conversations.
  • Support for custom llama.cpp builds. Toggles for Cache RAM, Mmap, Mlock, Checkpoints, Spe Decoding KV Cache, Vision On / Off
  • Unsloth Dynamic v3.0 is released. New Qwen3.8-27B Dynamic v3.0 GGUFs deliver >10% higher top-1 accuracy compared to everyone else. Works with Unsloth.
Auto compaction (Experimental)

You can now do long chats and surpass a model's context limit, with evicted turns remaining searchable.

  • Long local chats can continue past the context limit by rolling older turns out of active context.
  • Auto compaction creates fresh context epochs instead of permanently trimming replies.
  • Evicted conversations remain searchable, with improved fact recall.
  • Context window information is shown before chat begins.

How it works

  • Entire oldest turns are removed only when needed, never mid-message. The saved transcript stays unchanged.
  • Evicted turns are indexed into a per-thread searchable archive using Unsloth's existing RAG pipeline (store, chunker, embedder, retrieval). Lexical search is prioritized because chat recall is usually exact matches like names, numbers, or IDs.
  • A recall is forced during eviction instead of relying on the model to search itself. Later retrieval uses search_conversation.
  • The archive persists across epochs, allowing future compactions to recover previously evicted context.
  • No summarization: it showed little benefit and added ~190s per compaction.
Remote & LAN access (Preview)

Access Unsloth from another device on your network, managed from settings.

  • New dedicated Settings section for remote access.
  • Enable or disable LAN access without restarting.
  • Supports connection addresses, QR codes, and optional auto-start.
  • LAN access is disabled by default and requires changing the generated admin password.
Chat + Functionality improvements
  • Long chats are faster with optimized streaming and thread handling.
  • Projects organize chats, files, and workspaces together.
  • Chats remember composer settings, system prompts, and model sampling options.
  • Added prompt queueing and customizable keyboard shortcuts.
  • Added edit_file tool for partial file modifications.
  • Improved tool calling and MCP behavior.
Hardware + inference improvements
  • Support for custom llama.cpp builds.
  • Toggles for advanced settings - Cache RAM, Mmap, Mlock, Checkpoints, Speculative Decoding KV Cache, Vision On / Off
  • Better validation for missing GPU support and oversized GGUF models.
  • Improved MTP performance and VRAM handling.
  • Better compatibility across ROCm, xFormers, and flash-attention setups.
  • Added Intel XPU support.
API + serving
  • Responses API supports structured output formatting.
  • Improved recovery when llama-server crashes.
  • Added OpenCode V2 support for unsloth start.
Hub + Desktop + training
  • Hub supports more image/video workflows.
  • Faster and improved GGUF downloads.
  • Desktop packaging and permissions improved.
  • Training scheduler and preprocessing improvements.
What's Changed
New Contributors

Full Changelog: https://github.com/unslothai/unsloth/compare/v0.1.801-beta...v0.1.803-beta

View originalPermalink
How v0.1.803-beta went
v0.1.802-betaPre-release

Bug Fixes + Auto compaction + LAN Remote Access

Added 12
  • LAN API keyless and password-less access is now supported
  • XET and HTTP download toggle for clearer download progress
  • Auto Compaction (Experimental) for longer chats beyond context limits
  • Remote and LAN Access (Preview) for easy network access without Cloudflare links
  • Support for custom llama.cpp builds with toggles for Cache RAM, Mmap, Mlock, Checkpoints, Speculative Decoding KV Cache, and Vision On/Off
  • Unsloth Dynamic v3.0 released with new Qwen3.8-27B Dynamic v3.0 GGUFs delivering >10% higher top-1 accuracy
Changed 5
  • Faster Chat with improved streaming performance, reduced UI lag, and smoother long conversations
  • Improved tool calling and MCP behavior
  • Improved recovery when llama-server crashes
  • Improved MTP performance and VRAM handling
  • Better compatibility across ROCm, xFormers, and flash-attention setups
Fixed 2
  • MLX and Mac runtimes now run correctly
  • AMD bug fixes for Strix Halo and all RDNA GPUs

From unsloth

Thanks for the support for Qwen3.8-27B and Unsloth Desktop! This is a bug fix release with 170+ PRs.

  • MLX fixed - Some MLX and Mac runtimes did not run correctly
  • LAN API keyless / password-less is now supported
  • XET / HTTP download toggle - clearer download progress
  • AMD bug fixes for Strix Halo, all RDNA GPUs + 170 bug fixes
Features
  • Auto Compaction (Experimental) for longer chats beyond context limits
  • Remote & LAN Access (Preview) for easy network access without Cloudflare links
  • Faster Chat - Improved streaming performance, reduced UI lag, and smoother long conversations.
  • Support for custom llama.cpp builds. Toggles for Cache RAM, Mmap, Mlock, Checkpoints, Spe Decoding KV Cache, Vision On / Off
  • Unsloth Dynamic v3.0 is released. New Qwen3.8-27B Dynamic v3.0 GGUFs deliver >10% higher top-1 accuracy compared to everyone else. Works with Unsloth.
Auto compaction (Experimental)

You can now do long chats and surpass a model's context limit, with evicted turns remaining searchable.

  • Long local chats can continue past the context limit by rolling older turns out of active context.
  • Auto compaction creates fresh context epochs instead of permanently trimming replies.
  • Evicted conversations remain searchable, with improved fact recall.
  • Context window information is shown before chat begins.

How it works

  • Entire oldest turns are removed only when needed, never mid-message. The saved transcript stays unchanged.
  • Evicted turns are indexed into a per-thread searchable archive using Unsloth's existing RAG pipeline (store, chunker, embedder, retrieval). Lexical search is prioritized because chat recall is usually exact matches like names, numbers, or IDs.
  • A recall is forced during eviction instead of relying on the model to search itself. Later retrieval uses search_conversation.
  • The archive persists across epochs, allowing future compactions to recover previously evicted context.
  • No summarization: it showed little benefit and added ~190s per compaction.
Remote & LAN access (Preview)

Access Unsloth from another device on your network, managed from settings.

  • New dedicated Settings section for remote access.
  • Enable or disable LAN access without restarting.
  • Supports connection addresses, QR codes, and optional auto-start.
  • LAN access is disabled by default and requires changing the generated admin password.
Chat + Functionality improvements
  • Long chats are faster with optimized streaming and thread handling.
  • Projects organize chats, files, and workspaces together.
  • Chats remember composer settings, system prompts, and model sampling options.
  • Added prompt queueing and customizable keyboard shortcuts.
  • Added edit_file tool for partial file modifications.
  • Improved tool calling and MCP behavior.
Hardware + inference improvements
  • Support for custom llama.cpp builds.
  • Toggles for advanced settings - Cache RAM, Mmap, Mlock, Checkpoints, Speculative Decoding KV Cache, Vision On / Off
  • Better validation for missing GPU support and oversized GGUF models.
  • Improved MTP performance and VRAM handling.
  • Better compatibility across ROCm, xFormers, and flash-attention setups.
  • Added Intel XPU support.
API + serving
  • Responses API supports structured output formatting.
  • Improved recovery when llama-server crashes.
  • Added OpenCode V2 support for unsloth start.
Hub + Desktop + training
  • Hub supports more image/video workflows.
  • Faster and improved GGUF downloads.
  • Desktop packaging and permissions improved.
  • Training scheduler and preprocessing improvements.
What's Changed
New Contributors

Full Changelog: https://github.com/unslothai/unsloth/compare/v0.1.802-beta...v0.1.802-beta

View originalPermalink
How v0.1.802-beta went
v0.1.801-betaPre-release

Auto compaction (preview) + LAN Remote Access

Added 10
  • Auto Compaction (Experimental) for longer chats beyond context limits with evicted turns remaining searchable
  • Remote & LAN Access (Preview) for easy network access without Cloudflare links
  • Support for custom llama.cpp builds with toggles for Cache RAM, Mmap, Mlock, Checkpoints, Speculative Decoding KV Cache, and Vision On/Off
  • Unsloth Dynamic v3.0 with new Qwen3.8-27B Dynamic v3.0 GGUFs delivering >10% higher top-1 accuracy
  • Projects feature to organize chats, files, and workspaces together
  • Prompt queueing and customizable keyboard shortcuts
Changed 10
  • Improved streaming performance, reduced UI lag, and smoother long conversations
  • Chats now remember composer settings, system prompts, and model sampling options
  • Improved tool calling and MCP behavior
  • Better validation for missing GPU support and oversized GGUF models
  • Improved MTP performance and VRAM handling
  • Better compatibility across ROCm, xFormers, and flash-attention setups
Fixed 1
  • Improved recovery when llama-server crashes

From unsloth

Thanks for the support for Qwen3.8-27B and Unsloth Desktop last week! For this release, we merged 200+ PRs to introduce many new features, fixes including:

  • Auto Compaction (Experimental) for longer chats beyond context limits
  • Remote & LAN Access (Preview) for easy network access without Cloudflare links
  • Faster Chat - Improved streaming performance, reduced UI lag, and smoother long conversations.
  • Support for custom llama.cpp builds. Toggles for Cache RAM, Mmap, Mlock, Checkpoints, Spe Decoding KV Cache, Vision On / Off
  • Unsloth Dynamic v3.0 is released. New Qwen3.8-27B Dynamic v3.0 GGUFs deliver >10% higher top-1 accuracy compared to everyone else. Works with Unsloth.
Auto compaction (Experimental)

You can now do long chats and surpass a model's context limit, with evicted turns remaining searchable.

  • Long local chats can continue past the context limit by rolling older turns out of active context.
  • Auto compaction creates fresh context epochs instead of permanently trimming replies.
  • Evicted conversations remain searchable, with improved fact recall.
  • Context window information is shown before chat begins.

How it works

  • Entire oldest turns are removed only when needed, never mid-message. The saved transcript stays unchanged.
  • Evicted turns are indexed into a per-thread searchable archive using Unsloth's existing RAG pipeline (store, chunker, embedder, retrieval). Lexical search is prioritized because chat recall is usually exact matches like names, numbers, or IDs.
  • A recall is forced during eviction instead of relying on the model to search itself. Later retrieval uses search_conversation.
  • The archive persists across epochs, allowing future compactions to recover previously evicted context.
  • No summarization: it showed little benefit and added ~190s per compaction.
Remote & LAN access (Preview)

Access Unsloth from another device on your network, managed from settings.

  • New dedicated Settings section for remote access.
  • Enable or disable LAN access without restarting.
  • Supports connection addresses, QR codes, and optional auto-start.
  • LAN access is disabled by default and requires changing the generated admin password.
Chat + Functionality improvements
  • Long chats are faster with optimized streaming and thread handling.
  • Projects organize chats, files, and workspaces together.
  • Chats remember composer settings, system prompts, and model sampling options.
  • Added prompt queueing and customizable keyboard shortcuts.
  • Added edit_file tool for partial file modifications.
  • Improved tool calling and MCP behavior.
Hardware + inference improvements
  • Support for custom llama.cpp builds.
  • Toggles for advanced settings - Cache RAM, Mmap, Mlock, Checkpoints, Speculative Decoding KV Cache, Vision On / Off
  • Better validation for missing GPU support and oversized GGUF models.
  • Improved MTP performance and VRAM handling.
  • Better compatibility across ROCm, xFormers, and flash-attention setups.
  • Added Intel XPU support.
API + serving
  • Responses API supports structured output formatting.
  • Improved recovery when llama-server crashes.
  • Added OpenCode V2 support for unsloth start.
Hub + Desktop + training
  • Hub supports more image/video workflows.
  • Faster and improved GGUF downloads.
  • Desktop packaging and permissions improved.
  • Training scheduler and preprocessing improvements.
What's Changed
New Contributors

Full Changelog: https://github.com/unslothai/unsloth/compare/v0.1.800-beta...v0.1.801-beta

View originalPermalink
How v0.1.801-beta went
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 originalPermalink
How v0.1.800-beta went

v0.1.702-beta

Pre-release
Added 2
  • Added tool calling and web search for all external providers
  • Added ability to login with Codex subscription
Changed 5
  • Made VRAM usage tunable in UI
  • Improved inference speed by 10% and reduced VRAM usage
  • Improved AMD RDNA3 and RDNA4 support
  • Improved Strix Halo support
  • Improved Mac support
Fixed 5
  • Fixed bypass permissions not working for sandboxing
  • Fixed image diffusion and video generation
  • Fixed slow Windows downloading due to throttling
  • Fixed Mac asking to download command line tools
  • Fixed AMD Strix Halo not being detected

From unsloth

Unsloth Desktop is here! The first desktop app to run and train AI models locally. Research, export and deploy from the same open-source app on Windows, macOS and Linux.

v0.1.702-beta Update (August 13th)
  • Added tool calling / web search & more for all external providers
  • Fixed bypass permissions not working for sandboxing
  • UI and UX fixes - VRAM usage is now tunable
  • 10% faster inference + reduced VRAM usage and other perf fixes
  • Much better AMD RDNA3,4 + Strix Halo, Mac support
  • Image diffusion, video generation fixes
  • Can login with Codex subscription
  • Many bug fixes

🦥 Download Unsloth Desktop for Linux, Windows, MacOS

Here's what you can do with Unsloth Desktop:

  • Get up to 50% more accurate tool calling with self-healing calls and sandboxed code execution.
  • Run Muse Glimmer 30B, Kimi K3, Qwen3.8, DeepSeek-V4 Flash 0731, Gemma 4, and more.
  • Generate videos with MiniMax-H3, and create images and videos with other diffusion models at up to 2× faster inference on supported workflows.
  • Use unlimited private web search, Deep Research, RAG and MCP.
  • Export models to NVFP4, GGUF and other formats.
  • Access Unsloth remotely through Cloudflare HTTPS.
  • Run on CPU or multiple GPUs across NVIDIA, AMD, Intel and Mac.
  • Train models without code, using less time and VRAM.
  • Use local models through Unsloth's OpenAI-compatible API, or connect OpenAI and Anthropic models.
Tools, private research + APIs

Self-healing tool calling repairs malformed calls instead of dropping them. Models can run Python and Bash inside sandboxed environments, so they can test code, create files and verify their work.

Use unlimited private web search, let Deep Research plan and produce cited reports, or bring your own files into RAG. You can also connect MCP tools for workflows that need external apps, data or actions.

Local models can be served through Unsloth's OpenAI-compatible API for agents and other clients. Inside Desktop, you can also connect OpenAI and Anthropic as cloud model providers.

Muse Glimmer 30B + latest models

Run Muse Glimmer 30B locally for chat, agents, tools and APIs, alongside Kimi K3, Qwen3.8, DeepSeek-V4 Flash 0731 and Gemma 4. Download and manage them in one place through Unsloth Desktop.

MiniMax-H3 + image and video diffusion

Run MiniMax-H3 locally for video generation. Create images and videos locally, edit existing images and train supported diffusion models. Use LoRAs, reference images and ControlNet where available, with up to 2× faster inference on supported workflows.

No-code training, export + remote deployment

Pick a model and dataset, adjust the settings and start training. You can train supported LLMs, diffusion models, TTS models and embedding models without writing code. On supported LLM workloads, training is up to 2× faster and uses up to 70% less VRAM.

Export your trained models to NVFP4, GGUF and other supported formats. You can also securely deploy and access models remotely: turn on Remote access to publish Unsloth through a Cloudflare HTTPS link, then use the app and its local APIs from another device.

Hardware + platform support

Unsloth Desktop runs on Windows, macOS and Linux. Hardware support spans CPU and multi-GPU systems, NVIDIA and AMD GPUs, Intel hardware, and Mac.

CPU support includes Chat and Data Recipes. Training and inference options vary by model and backend.

Download Unsloth Desktop

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

  • Windows
  • macOS
  • Linux

🦥 Download Unsloth Desktop

Star Unsloth on GitHub

v0.1.701-beta Update (1PM PDT time August 11th)
  • Fixed slow Windows downloading (200x faster due to throttling)
  • Fixed Mac asking to download command line tools (uv bug)
  • Fixed AMD Strix Halo not being detected
  • Other bug fixes
View originalPermalink
How v0.1.702-beta went
v0.1.701-betaPre-release

Introducing Unsloth Desktop 🦥

Added 11
  • Unsloth Desktop application for running and training AI models locally on Windows, macOS and Linux
  • Self-healing tool calling that repairs malformed calls and executes sandboxed code
  • Support for running Muse Glimmer 30B, Kimi K3, Qwen3.8, DeepSeek-V4 Flash 0731, and Gemma 4 models
  • MiniMax-H3 video generation and image/video diffusion model support
  • Unlimited private web search, Deep Research, RAG and MCP support
  • Model export to NVFP4, GGUF and other formats
Changed 2
  • Training up to 2× faster and using up to 70% less VRAM on supported LLM workloads
  • Image and video inference up to 2× faster on supported workflows
Fixed 3
  • Slow Windows downloading by fixing throttling issue, achieving 200× faster speeds
  • Mac command line tools download requirement caused by uv bug
  • AMD Strix Halo GPU detection

From unsloth

Unsloth Desktop is here! The first desktop app to run and train AI models locally. Research, export and deploy from the same open-source app on Windows, macOS and Linux.

🦥 Download Unsloth Desktop for Linux, Windows, MacOS

Here's what you can do with Unsloth Desktop:

  • Get up to 50% more accurate tool calling with self-healing calls and sandboxed code execution.
  • Run Muse Glimmer 30B, Kimi K3, Qwen3.8, DeepSeek-V4 Flash 0731, Gemma 4, and more.
  • Generate videos with MiniMax-H3, and create images and videos with other diffusion models at up to 2× faster inference on supported workflows.
  • Use unlimited private web search, Deep Research, RAG and MCP.
  • Export models to NVFP4, GGUF and other formats.
  • Access Unsloth remotely through Cloudflare HTTPS.
  • Run on CPU or multiple GPUs across NVIDIA, AMD, Intel and Mac.
  • Train models without code, using less time and VRAM.
  • Use local models through Unsloth's OpenAI-compatible API, or connect OpenAI and Anthropic models.
Tools, private research + APIs

Self-healing tool calling repairs malformed calls instead of dropping them. Models can run Python and Bash inside sandboxed environments, so they can test code, create files and verify their work.

Use unlimited private web search, let Deep Research plan and produce cited reports, or bring your own files into RAG. You can also connect MCP tools for workflows that need external apps, data or actions.

Local models can be served through Unsloth's OpenAI-compatible API for agents and other clients. Inside Desktop, you can also connect OpenAI and Anthropic as cloud model providers.

Muse Glimmer 30B + latest models

Run Muse Glimmer 30B locally for chat, agents, tools and APIs, alongside Kimi K3, Qwen3.8, DeepSeek-V4 Flash 0731 and Gemma 4. Download and manage them in one place through Unsloth Desktop.

MiniMax-H3 + image and video diffusion

Run MiniMax-H3 locally for video generation. Create images and videos locally, edit existing images and train supported diffusion models. Use LoRAs, reference images and ControlNet where available, with up to 2× faster inference on supported workflows.

No-code training, export + remote deployment

Pick a model and dataset, adjust the settings and start training. You can train supported LLMs, diffusion models, TTS models and embedding models without writing code. On supported LLM workloads, training is up to 2× faster and uses up to 70% less VRAM.

Export your trained models to NVFP4, GGUF and other supported formats. You can also securely deploy and access models remotely: turn on Remote access to publish Unsloth through a Cloudflare HTTPS link, then use the app and its local APIs from another device.

Hardware + platform support

Unsloth Desktop runs on Windows, macOS and Linux. Hardware support spans CPU and multi-GPU systems, NVIDIA and AMD GPUs, Intel hardware, and Mac.

CPU support includes Chat and Data Recipes. Training and inference options vary by model and backend.

Download Unsloth Desktop

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

  • Windows
  • macOS
  • Linux

🦥 Download Unsloth Desktop

Star Unsloth on GitHub

v0.1.701-beta Update (1PM PDT time August 11th)
  • Fixed slow Windows downloading (200x faster due to throttling)
  • Fixed Mac asking to download command line tools (uv bug)
  • Fixed AMD Strix Halo not being detected
  • Other bug fixes
View originalPermalink
How v0.1.701-beta went
v0.1.70-betaPre-release

Introducing Unsloth Desktop 🦥

Added 12
  • Unsloth Desktop app for running and training AI models locally on Windows, macOS and Linux
  • Self-healing tool calling that repairs malformed calls and executes sandboxed code
  • Support for running Muse Glimmer 30B, Kimi K3, Qwen3.8, DeepSeek-V4 Flash 0731, and Gemma 4 models
  • MiniMax-H3 for local video generation with up to 2× faster inference on supported workflows
  • Private web search, Deep Research, RAG and MCP capabilities
  • Model export to NVFP4, GGUF and other formats

From unsloth

Unsloth Desktop is here! The first desktop app to run and train AI models locally. Research, export and deploy from the same open-source app on Windows, macOS and Linux.

🦥 Download Unsloth Desktop for Linux, Windows, MacOS

Here's what you can do with Unsloth Desktop:

  • Get up to 50% more accurate tool calling with self-healing calls and sandboxed code execution.
  • Run Muse Glimmer 30B, Kimi K3, Qwen3.8, DeepSeek-V4 Flash 0731, Gemma 4, and more.
  • Generate videos with MiniMax-H3, and create images and videos with other diffusion models at up to 2× faster inference on supported workflows.
  • Use unlimited private web search, Deep Research, RAG and MCP.
  • Export models to NVFP4, GGUF and other formats.
  • Access Unsloth remotely through Cloudflare HTTPS.
  • Run on CPU or multiple GPUs across NVIDIA, AMD, Intel and Mac.
  • Train models without code, using less time and VRAM.
  • Use local models through Unsloth's OpenAI-compatible API, or connect OpenAI and Anthropic models.
Tools, private research + APIs

Self-healing tool calling repairs malformed calls instead of dropping them. Models can run Python and Bash inside sandboxed environments, so they can test code, create files and verify their work.

Use unlimited private web search, let Deep Research plan and produce cited reports, or bring your own files into RAG. You can also connect MCP tools for workflows that need external apps, data or actions.

Local models can be served through Unsloth's OpenAI-compatible API for agents and other clients. Inside Desktop, you can also connect OpenAI and Anthropic as cloud model providers.

Muse Glimmer 30B + latest models

Run Muse Glimmer 30B locally for chat, agents, tools and APIs, alongside Kimi K3, Qwen3.8, DeepSeek-V4 Flash 0731 and Gemma 4. Download and manage them in one place through Unsloth Desktop.

MiniMax-H3 + image and video diffusion

Run MiniMax-H3 locally for video generation. Create images and videos locally, edit existing images and train supported diffusion models. Use LoRAs, reference images and ControlNet where available, with up to 2× faster inference on supported workflows.

No-code training, export + remote deployment

Pick a model and dataset, adjust the settings and start training. You can train supported LLMs, diffusion models, TTS models and embedding models without writing code. On supported LLM workloads, training is up to 2× faster and uses up to 70% less VRAM.

Export your trained models to NVFP4, GGUF and other supported formats. You can also securely deploy and access models remotely: turn on Remote access to publish Unsloth through a Cloudflare HTTPS link, then use the app and its local APIs from another device.

Hardware + platform support

Unsloth Desktop runs on Windows, macOS and Linux. Hardware support spans CPU and multi-GPU systems, NVIDIA and AMD GPUs, Intel hardware, and Mac.

CPU support includes Chat and Data Recipes. Training and inference options vary by model and backend.

Download Unsloth Desktop

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

  • Windows
  • macOS
  • Linux

🦥 Download Unsloth Desktop

Star Unsloth on GitHub

View originalPermalink
How v0.1.70-beta went
v0.1.62-betaPre-release

Unsloth v0.1.62-beta

Many bug fixes

View originalPermalink
How v0.1.62-beta went
v0.1.61-betaPre-release

Meta Muse Glimmer

Added 7
  • Support for Meta Muse Glimmer 30B model with Unsloth and Unsloth Dynamic quants
  • MiniMax-H3 video generation support
  • Preliminary image diffusion support
  • Chat now provides downloadable artifacts
  • Qwen3-ASR dictation support
  • Cancellable downloads with download prompt
  • Support for independent prompt queues across parallel chats
Changed 4
  • Revamped training page
  • Desktop update controls moved to Settings > General
  • Studio Video moved under More section until user pins it
  • Studio sidebar menu separators now visible in dark mode
Fixed 9
  • Studio cached-pipeline signals now judged on the snapshot the row actually loads
  • Fix stale response-model label assertion
  • Studio detect stalled Deep Research output streams
  • Studio generated media now displays unrounded with fixed selected thumbnail
  • Desktop warn before quitting during an update and skip installer fallback on cancel
  • Studio tooltip no longer hangs over dialogs when clicked

From unsloth

Meta has released Muse Glimmer, the first open model from Meta Superintelligence Labs. Muse Glimmer is a dense, 30B parameter model by Meta, built for local agentic and coding workflows. Released under the Apache 2.0 license you can run Muse Glimmer 30B via Unsloth and Unsloth Dynamic quants for the best performance.

Run Muse Glimmer Fine-tune Muse Glimmer

Muse Glimmer 30B can run locally on 20GB RAM/VRAM setups, including Mac and GPUs. You can also train and fine-tune Muse Glimmer 30B using Unsloth on 20GB VRAM.

Other Updates
  • MiniMax-H3 video generation support
  • Preliminary image diffusion support
  • Revamped training page
  • Chat now provides downloadable artifacts
Updating / installing Unsloth

macOS, Linux, WSL:

curl -fsSL https://unsloth.ai/install.sh | sh

Windows:

irm https://unsloth.ai/install.ps1 | iex
What's Changed
New Contributors

Full Changelog: https://github.com/unslothai/unsloth/compare/v0.1.52-beta...v0.1.60-beta

View originalPermalink
How v0.1.61-beta went

More in AI

View all
codex

codex release notes.

codex
Ollama

Get up and running with large language models locally.

Ollama
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

openclaw
tensorflow

An Open Source Machine Learning Framework for Everyone

tensorflow
superpowers

An agentic skills framework & software development methodology that works.

obra
skills

Skills for Real Engineers. Straight from my .agents directory.

mattpocock

Discussion

If you publish unsloth, you can claim this product by proving you administer its repository.