← Back to community benchmarks
GLM-5.2-DQ4plus-q8
Performance
64k
tokens
164.9
PP tok/s
13.1
TG tok/s
397341
TTFT (ms)
441.8
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.5.3
macOS
macOS 26.5.2
Context
65,536