← Back to community benchmarks

GLM-4.7-Flash

M3 Ultra (60c) · 96 GB · 6bit · 2026-03-09
Performance
32k
tokens
508.5
PP tok/s
31.6
TG tok/s
64438
TTFT (ms)
32.9
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 96 GB
GPU Cores 60
Software
oMLX v0.2.6
macOS macOS 26.3.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,069 61.4 23.3 GB view
4k 1,290 55.9 24.3 GB view
8k 1,109 50.4 25.5 GB view
16k 802.4 41.4 27.9 GB view
32k 508.5 31.6 32.9 GB current
64k 282.9 21.0 43.0 GB view
Batching Results
Batch Size TG tok/s Speedup
61.4 1.00×
92.6 1.51×
136.4 2.22×
172.6 2.81×