X · @huggingface
· X / Twitter
RT Xenova: Bonsai 27B just changed the local LLM game forever. 1-bit quantization shrinks it from 54GB to just 3.8GB (-93%), while retaining 90% of it…
RT XenovaBonsai 27B just changed the local LLM game forever.1-bit quantization shrinks it from 54GB to just 3.8GB (-93%), while retaining 90% of its intelligence. That's insane.With custom WebGPU kernels written by Fable 5 and GPT 5.6 Sol, the model now runs locally in your browser!