← Back to community benchmarks

GLM-4.7-Flash

M5 Max (40c) · 128 GB · 8bit · 2026-07-24

Performance

64k

tokens

433.1

PP tok/s

35.6

TG tok/s

151305

TTFT (ms)

50.0

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.5.1

macOS macOS 26.3.2

Context 65,536