← Back to community benchmarks

GLM-4.6V-Flash

M5 Pro (20c) · 64 GB · 6bit · 2026-03-16

Performance

4k

tokens

347.6

PP tok/s

28.3

TG tok/s

11782

TTFT (ms)

9.6

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.2.14

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	355.7	29.5	9.7 GB	view
4k	347.6	28.3	9.6 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	29.5	1.00×
2×	52.4	1.78×
4×	68.6	2.33×