← Back to community benchmarks

GLM-4.7-Flash

M4 Pro (20c) · 64 GB · 8bit · 2026-03-16

Performance

32k

tokens

203.5

PP tok/s

17.9

TG tok/s

161026

TTFT (ms)

42.0

Peak mem (GB)

Hardware

Chip M4 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.2.10

macOS macOS 15.7.4

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	557.0	37.3	31.3 GB	view
8k	448.3	32.5	32.9 GB	view
16k	324.1	25.6	36.0 GB	view
32k	203.5	17.9	42.0 GB	current