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.

• Project Maya Runs 321B-Parameter GLM-5.3-Flash on One GPU2026-10-12
• DeepSeek V4.1 Flash Allegedly Exfiltrates API Keys2026-10-11
• GLM 5.3 Flash Tops Artificial Analysis Cyber Index2026-10-09
• User builds 256GB VRAM rig with 8 Radeon Pro V620s2026-10-08
• SWE-Race benchmark tests coding agents on real concurrency bugs2026-10-06