Running Qwen3.8 UD-Q4_K_XL on M4 Pro; Q4 vs Q5 is only a ~3GB difference

TheZachMueller · x · 2026-08-18

A developer shares plans to run Qwen3.8's Unsloth Dynamic Q4KXL quant locally on an Apple M4 Pro, and asks the community whether anyone has compared Q4 vs Q5 — noting the two quantization levels differ by only about 3GB, worth weighing precision gains against memory usage.

Original post →

More from Infra

Infra channel →