← Back to community benchmarks

GLM-4.5-Air-REAP-82B-A12B5Bit

M5 Max (40c) · 128 GB · 5bit · 2026-05-10

Performance

64k

tokens

347.8

PP tok/s

10.4

TG tok/s

188404

TTFT (ms)

65.1

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 65,536