The A.I. Daily
M5 Ultra 256 runs GLM 5.3 Flash at 68.8 tok/s
A user reports running GLM 5.3 Flash with oQ4e+MTP quantization on oMLX 0.7.0 on an M5 Ultra 256, achieving 68.8 tok/s decode and 1,878 tok/s prefill, with more optimization to come. The result responds to earlier benchmarks that were lower than expected.