← Back to community benchmarks
GLM-4.7-8bit-gs32
Performance
16k
tokens
184.3
PP tok/s
9.0
TG tok/s
88876
TTFT (ms)
376.7
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.2.6
macOS
macOS 15.5
Context
16,384