← Back to community benchmarks

GLM-4___7

M3 Ultra (80c) · 512 GB · 6bit · 2026-03-12
Performance
1k
tokens
233.3
PP tok/s
16.6
TG tok/s
4388
TTFT (ms)
268.3
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.2.6
macOS macOS 15.3
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 233.3 16.6 268.3 GB current
4k 239.0 14.8 269.7 GB view
Batching Results
Batch Size TG tok/s Speedup
1× 16.6 1.00×
2× 23.2 1.40×
4× 29.4 1.77×