Features
Interactive tree diagram of entire conversation
Fork, merge, and prune conversation branches
Selective context injection – control exactly which nodes are sent to the LLM
Visual diff of context windows
Branch comparison side-by-side
Export conversation tree as JSON (Pro)
Node tagging and colour-coding
Smart search across entire tree
Context window size indicator
Custom CUDA kernels for LoRA, FP8, full fine-tuning
Up to 2x faster training vs Flash Attention 2
Up to 90% less memory usage vs Flash Attention 2
Unsloth Studio no-code visual interface (offline on Mac/Windows)
Data Recipes auto-create datasets from PDF, CSV, JSON
Model Arena side-by-side model comparison
Export to GGUF and safetensors
OpenAI-compatible API endpoint
Tool-calling and web search capability
Run 100% offline on Mac and Windows
Supports 500+ models (text, vision, audio, embeddings)
Reinforcement learning (GRPO) with 80% less VRAM
Multi-GPU support (Pro, coming to Free)
Multi-node support (Enterprise only)
Quantization-Aware Training (QAT)
