← Back to community benchmarks

GLM-4___7-Flash

M3 Ultra (80c) · 512 GB · bf16 · 2026-03-15
Performance
32k
tokens
621.8
PP tok/s
28.5
TG tok/s
52697
TTFT (ms)
65.9
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.2.12
macOS macOS 15.3
Context 32,768