← Back to community benchmarks

GLM-4.7-Flash

M3 Ultra (80c) · 512 GB · 4bit · 2026-03-12
Performance
4k
tokens
1,648
PP tok/s
66.3
TG tok/s
2485
TTFT (ms)
17.6
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.2.9
macOS macOS 26.3
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,165 70.9 16.4 GB view
4k 1,648 66.3 17.6 GB current
8k 1,421 58.8 19.1 GB view
16k 1,012 50.5 21.0 GB view
32k 628.3 37.1 25.9 GB view
64k 342.9 23.1 36.0 GB view
Batching Results
Batch Size TG tok/s Speedup
70.9 1.00×
114.1 1.61×
185.0 2.61×