← Back to community benchmarks

GLM-4.7-Flash

M2 Ultra (76c) · 192 GB · 8bit · 2026-03-10

Performance

4k

tokens

906.0

PP tok/s

47.5

TG tok/s

4521

TTFT (ms)

31.3

Peak mem (GB)

Hardware

Chip M2 Ultra (76c)

Memory 192 GB

GPU Cores 76

Software

oMLX v0.2.7

macOS macOS 15.7

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	675.8	50.4	30.3 GB	view
4k	906.0	47.5	31.3 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	50.4	1.00×
2×	84.2	1.67×
4×	132.8	2.63×