← Back to community benchmarks

GLM-4.7-Flash

M5 Pro (20c) · 64 GB · 8bit · 2026-03-28
Performance
1k
tokens
1,322
PP tok/s
51.1
TG tok/s
774
TTFT (ms)
30.3
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.2.24
macOS macOS 26.4
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,322 51.1 30.3 GB current
4k 1,290 44.9 31.3 GB view
8k 1,005 38.6 32.8 GB view
16k 667.4 32.3 35.9 GB view
32k 383.9 23.7 42.0 GB view
64k 209.0 15.5 54.3 GB view
Batching Results
Batch Size TG tok/s Speedup
51.1 1.00×
71.4 1.40×
88.8 1.74×