← Back to community benchmarks

GLM-4.7-8bit-gs32

M3 Ultra (80c) · 512 GB · 8bit · 2026-03-10

Performance

1k

tokens

221.9

PP tok/s

13.3

TG tok/s

4614

TTFT (ms)

370.9

Peak mem (GB)

Hardware

Chip M3 Ultra (80c)

Memory 512 GB

GPU Cores 80

Software

oMLX v0.2.6

macOS macOS 15.5

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	221.9	13.3	370.9 GB	current
4k	236.0	12.1	372.4 GB	view
8k	216.9	10.8	373.8 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	13.3	1.00×
8×	35.0	2.63×