← Back to community benchmarks

GLM-4.6V-Flash

M2 Pro (19c) · 16 GB · 4bit · 2026-03-10

Performance

4k

tokens

157.0

PP tok/s

26.0

TG tok/s

26087

TTFT (ms)

7.5

Peak mem (GB)

Hardware

Chip M2 Pro (19c)

Memory 16 GB

GPU Cores 19

Software

oMLX v0.2.6

macOS macOS 26.2

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	162.2	24.8	7.5 GB	view
4k	157.0	26.0	7.5 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	24.8	1.00×
2×	38.6	1.56×
4×	40.7	1.64×