← Back to community benchmarks

GLM-4.7-Flash

M3 Max (30c) · 36 GB · 4bit · 2026-04-18
Performance
1k
tokens
752.2
PP tok/s
60.3
TG tok/s
1361
TTFT (ms)
16.4
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 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 752.2 60.3 16.4 GB current
4k 707.2 51.9 17.6 GB view
8k 572.4 42.9 19.1 GB view