Unsloth AI

2026•Unsloth AI

Unsloth Studio vBeta

Unsloth Studio is an open-source, no-code web interface designed for training, running, and exporting AI models locally. It supports a wide range of models, including text, vision, TTS audio, and embedding models, enabling users to fine-tune and deploy them efficiently without requiring extensive technical expertise.

Run GGUF and safetensor models locally on Mac, Windows, and Linux

Train over 500 models 2x faster with 70% less VRAM usage

Support for text, vision, TTS audio, and embedding models

PricingFree

VersionBeta

2026•Unsloth AI

Unsloth v0.1.37-beta v0.1.37-beta

Paid

Unsloth

Fine-Tuning

A major update to Unsloth's open-source local fine-tuning and inference platform. Includes a revamped Studio UI, collapsible sidebar, AMD Linux support, and a new Preserve Thinking toggle.

Revamped Unsloth Studio UI/UX with collapsible sidebar and chat history search

Preliminary AMD GPU support for Linux users

New Preserve Thinking toggle and fixed inference token/s reporting

PricingFree (open source)

Version0.1.37-beta

2026•Unsloth AI

Qwen3.6 GGUFs v3.6

Paid

LLM

GGUF

Unsloth AI released experimental GGUFs for Qwen3.6 in 27B and 35B variants, featuring a new Multi-Token Prediction (MTP) architecture that delivers up to 220 tokens/s on a single GPU — a 1.4x speed-up over previous versions. The 27B model runs on 18GB RAM and the 35B-A3B on 22GB, making high-quality local inference more accessible.

MTP (Multi-Token Prediction) architecture for up to 220 tokens/s on a single GPU

27B model runs on 18GB RAM; 35B-A3B runs on 22GB

1.4x speed improvement over previous Qwen GGUF versions

PricingFree (Open Source)

Version3.6