← Back to community benchmarks

glm-4.7-flash-nvpf4-bfloat16

M1 Max (32c) · 64 GB · 4bit · 2026-05-10
Performance
4k
tokens
397.5
PP tok/s
37.3
TG tok/s
10303
TTFT (ms)
17.6
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.9.dev1
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 397.5 37.3 17.6 GB current
32k 159.0 18.0 28.3 GB view