← Back to community benchmarks

GLM-4.6V-Flash

M3 Ultra (80c) · 512 GB · 4bit · 2026-03-15

Performance

4k

tokens

1,229

PP tok/s

64.2

TG tok/s

3332

TTFT (ms)

7.5

Peak mem (GB)

Hardware

Chip M3 Ultra (80c)

Memory 512 GB

GPU Cores 80

Software

oMLX v0.2.11

macOS macOS 15.5

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,245	69.3	7.5 GB	view
4k	1,229	64.2	7.5 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	69.3	1.00×
2×	128.2	1.85×
4×	194.4	2.81×