Running 5 5 OS1 (Ultravox Llama 3.2 1b + Kokoro TTS + Whisper) 💻 In-browser local conversational AI inspired by 'Her'
70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float Paper • 2504.11651 • Published 12 days ago • 26
Unsloth Dynamic 2.0 Quants Collection New 2.0 version of our Dynamic GGUF + Quants. Dynamic 2.0 achieves superior accuracy & outperforms all leading quantization methods. • 17 items • Updated about 1 hour ago • 43