{"id":1282,"date":"2026-09-17T16:56:58","date_gmt":"2026-09-17T07:56:58","guid":{"rendered":"https:\/\/localmodelwatch.tsuchitsuchi.com\/engine-unsloth-en\/"},"modified":"2026-10-31T00:10:46","modified_gmt":"2026-10-30T15:10:46","slug":"engine-unsloth-en","status":"publish","type":"page","link":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/engine-unsloth-en\/","title":{"rendered":"Unsloth: Releases and Overview"},"content":{"rendered":"

Library for fast, low-VRAM fine-tuning (LoRA \/ QLoRA). Also known for GGUF export and its Dynamic 2.0 quantized releases.<\/p>\n

Category: Quantization, model formats and fine-tuning. Part of our engine and tool tracker<\/a>.<\/em><\/p>\n

At a Glance<\/h2>\n
\n\n\n\n\n\n\n\n\n\n\n
Item<\/th>\nValue<\/th>\n<\/tr>\n<\/thead>\n
Repository<\/td>\nunslothai\/unsloth<\/a><\/td>\n<\/tr>\n
License<\/td>\nApache-2.0<\/td>\n<\/tr>\n
Main language<\/td>\nPython<\/td>\n<\/tr>\n
GitHub stars<\/td>\n76,273 (as of 2026-09-17)<\/td>\n<\/tr>\n
Latest release<\/td>\nv0.1.913-beta<\/a> (2026-10-30)<\/td>\n<\/tr>\n
Install \/ docs<\/td>\nofficial documentation<\/a><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n

The project describes itself as: \u201cLocal UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.\u201d<\/p>\n

Release History<\/h2>\n

Compiled by Local Model Watch from the project’s GitHub releases. Pre-releases are omitted. Where we wrote an article about a release, it is linked in the last column; smaller releases are tracked here only.<\/em><\/p>\n

\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
Version<\/th>\nReleased<\/th>\nRelease notes<\/th>\nOur article<\/th>\n<\/tr>\n<\/thead>\n
v0.1.913-beta (Customize + Performance + UI\/UX improvements)<\/td>\n2026-10-30<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.912-beta (Trick or Treat + Optimizations)<\/td>\n2026-10-28<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.911-beta (Scheduled + MiniMax-M3.1-Flash + Perf Gains)<\/td>\n2026-10-26<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.910-beta (MOSS-Image, Flint & NVIDIA Bolt E4B)<\/td>\n2026-10-24<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.909-beta (DeepSeek-V4.1 & FLUX-3)<\/td>\n2026-10-20<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.908-beta (Meta Muse Spark Open + NVIDIA Nemotron 3.5)<\/td>\n2026-10-16<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.907-beta (Large Performance Gains + More Browser Use)<\/td>\n2026-10-14<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.906-beta (Browser Use + Qwen-Image-2.1-Turbo)<\/td>\n2026-10-12<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.905-beta (Sandboxing is here!)<\/td>\n2026-10-09<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.904-beta (Train your own Decision model)<\/td>\n2026-10-07<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.903-beta (New Browser + Voice Cloning)<\/td>\n2026-10-07<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.902-beta (Command Palette + Desktop UI\/UX)<\/td>\n2026-10-01<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.901-beta (Command Palette + Desktop UI\/UX)<\/td>\n2026-10-01<\/td>\nGitHub<\/a><\/td>\nUnsloth v0.1.901-beta Released: Major LoRA Memory Reductions<\/a><\/td>\n<\/tr>\n
v0.1.900-beta (Laya Decision Models + Library)<\/td>\n2026-09-28<\/td>\nGitHub<\/a><\/td>\nunsloth Desktop v0.1.900-beta Released with Laya and Speedups<\/a><\/td>\n<\/tr>\n
prebuilt-wheels-cu13 (Flash-Attention2, Causal-Conv1D, Mamba_SSM Binaries)<\/td>\n2026-09-27<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.815-beta (Qwen-Image-2.1 + Skills)<\/td>\n2026-09-23<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.814-beta (Qwen-Image-2.1 + Skills)<\/td>\n2026-09-23<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.813-beta (Qwen-Image-2.1 + Skills)<\/td>\n2026-09-23<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.812-beta (Qwen-Image-2.1 + Skills)<\/td>\n2026-09-23<\/td>\nGitHub<\/a><\/td>\nUnsloth Update: Qwen-Image-2.1 Support and Agent Skills Added<\/a><\/td>\n<\/tr>\n
v0.1.811-beta (Docker + Multi User + AMD Support)<\/td>\n2026-09-19<\/td>\nGitHub<\/a><\/td>\nUnsloth v0.1.811-beta Released with AMD & NVIDIA Docker Images<\/a><\/td>\n<\/tr>\n
v0.1.810-beta (Docker + Multi User + AMD Support)<\/td>\n2026-09-17<\/td>\nGitHub<\/a><\/td>\nUnsloth v0.1.810-beta Released with Multi-User and AMD Support<\/a><\/td>\n<\/tr>\n
Windows-ARM64 (Windows ARM64 Binaries)<\/td>\n2026-09-16<\/td>\nGitHub<\/a><\/td>\nUnsloth Now Supports Windows ARM64 for Local LLMs<\/a><\/td>\n<\/tr>\n
v0.1.808-beta (Large Performance Gains + Fixes)<\/td>\n2026-09-10<\/td>\nGitHub<\/a><\/td>\nUnsloth v0.1.808-beta Released: Major Performance Boosts<\/a><\/td>\n<\/tr>\n
v0.1.807-beta (Large Perf Improvements + Fixes)<\/td>\n2026-09-08<\/td>\nGitHub<\/a><\/td>\nUnsloth v0.1.807-beta Released with AMD and Apple Silicon Boosts<\/a><\/td>\n<\/tr>\n
v0.1.806-beta (2x Faster Qwen3.8-Flash + GLM-5.3-Flash MTP)<\/td>\n2026-09-02<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.805-beta (2x Faster Qwen3.8-Flash + GLM-5.3-Flash MTP)<\/td>\n2026-09-02<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.804-beta (Qwen3.8-Flash-Next + GLM-5.3-Flash)<\/td>\n2026-08-27<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.803-beta (Bug Fixes + Auto compaction + LAN Remote Access)<\/td>\n2026-08-25<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.802-beta (Bug Fixes + Auto compaction + LAN Remote Access)<\/td>\n2026-08-25<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.801-beta (Auto compaction (preview) + LAN Remote Access)<\/td>\n2026-08-21<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.800-beta (Qwen3.8-27B)<\/td>\n2026-08-14<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.702-beta<\/td>\n2026-08-14<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.701-beta (Introducing Unsloth Desktop \ud83e\udda5)<\/td>\n2026-08-12<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.70-beta (Introducing Unsloth Desktop \ud83e\udda5)<\/td>\n2026-08-12<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.62-beta<\/td>\n2026-08-11<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.61-beta (Meta Muse Glimmer)<\/td>\n2026-08-10<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.60-beta (Meta Muse Glimmer)<\/td>\n2026-08-10<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.527-beta<\/td>\n2026-08-10<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.526-beta (DSpark + DeepSeek-V4 Flash 0731)<\/td>\n2026-08-05<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.512-beta ( Kimi K3 + DeepSeek-V4 Flash 0731 + Deep Research + Parallel Chat)<\/td>\n2026-07-30<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.501-beta (Introducing AMD support)<\/td>\n2026-07-20<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.49-beta (New Personalization and Language Support!)<\/td>\n2026-07-16<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.481-beta (DeepSeek-V4 + NVFP4 Exporting)<\/td>\n2026-07-07<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.471-beta (GLM 5.2 + Model Hub + 3x longer contexts)<\/td>\n2026-06-19<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.464-beta (DiffusionGemma + Gemma 4 MTP)<\/td>\n2026-06-12<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.451-beta (Gemma 4 MTP + Bug Fixes)<\/td>\n2026-06-11<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.44-beta (Gemma 4 12B, New UI, MCP, Projects)<\/td>\n2026-06-03<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.43-beta (CUDA 13.3, Windows, Mac update)<\/td>\n2026-05-31<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.42-beta (An Update before Revamp!)<\/td>\n2026-05-26<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.41-beta (MTP + Studio fixes)<\/td>\n2026-05-19<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.405-beta (Qwen3.6 MTP and API \/ Connections)<\/td>\n2026-05-18<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.39-beta (New Unsloth API Inference Endpoint)<\/td>\n2026-05-05<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.37-beta (New UI Redesign + Qwen3.6)<\/td>\n2026-04-23<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.36-beta (Gemma 4 Fixes)<\/td>\n2026-04-08<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.35-beta (Google – Gemma 4 now in Unsloth!)<\/td>\n2026-04-03<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.3-beta (+50% tool call accuracy)<\/td>\n2026-04-01<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.25-beta (New Important Updates!)<\/td>\n2026-03-28<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
v0.1.2-beta (First Release post Unsloth Studio!)<\/td>\n2026-03-26<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
b8475<\/td>\n2026-03-23<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n
b8457<\/td>\n2026-03-21<\/td>\nGitHub<\/a><\/td>\n\u2014<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n

Articles on Local Model Watch<\/h2>\n