← Back to community benchmarks

GLM-4.7-Flash

M3 Max (30c) · 36 GB · 4bit · 2026-04-18
Performance
8k
tokens
572.4
PP tok/s
42.9
TG tok/s
14311
TTFT (ms)
19.1
Peak mem (GB)
Hardware
Chip M3 Max (30c)
Memory 36 GB
GPU Cores 30
Software
oMLX v0.3.6
macOS macOS 15.7.5
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 752.2 60.3 16.4 GB view
4k 707.2 51.9 17.6 GB view
8k 572.4 42.9 19.1 GB current