← Back to community benchmarks

glm4_flash

M3 Max (40c) · 64 GB · 4bit · 2026-03-11
Performance
1k
tokens
865.6
PP tok/s
66.9
TG tok/s
1183
TTFT (ms)
16.4
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.2.7
macOS macOS 15.7.4
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 865.6 66.9 16.4 GB current
4k 925.6 59.7 17.6 GB view
8k 726.2 50.8 19.1 GB view
16k 464.2 39.6 21.0 GB view
Batching Results
Batch Size TG tok/s Speedup
66.9 1.00×
102.3 1.53×
129.0 1.93×