Features
Visual environment builder
Python SDK for programmatic control
Versioned environments with rollback
Integration with OpenAI Gym
Integration with Stable-Baselines3
Custom observation and action spaces
Termination condition configuration
Environment sharing via links
Bulk environment import/export (JSON)
Telemetry and logging of RL runs
Real-time collaboration features (Team plan)
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)
