Streaming 1.6TB of K3 weights on an M5 Max 128GB is still slow

antirez · x · 2026-07-29

The post says streaming the official K3 Hugging Face weights is “a bit slow,” even when run directly on an M5 Max with 128GB of memory. The key detail is the scale of the model assets: 1.6TB of weights in mxfp4 format.

Related event: Tinkering with Local Quantized K3 Inference on Mac Hardware(2 posts)→

Original post →

More from Infra

Infra channel →