← Back to community benchmarks

GLM-4.7-8bit-gs32

M3 Ultra (80c) · 512 GB · 8bit · 2026-03-10
Performance
1k
tokens
222.6
PP tok/s
13.4
TG tok/s
4600
TTFT (ms)
370.9
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.2.6
macOS macOS 15.5
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 222.6 13.4 370.9 GB current
4k 235.4 12.1 372.4 GB view
8k 216.8 10.9 373.8 GB view
16k 184.3 9.0 376.7 GB view