← Back to community benchmarks

glm-4.6vmxfp8

M2 Ultra (76c) · 192 GB · 8bit · 2026-03-08
Performance
16k
tokens
259.9
PP tok/s
18.2
TG tok/s
63045
TTFT (ms)
108.2
Peak mem (GB)
Hardware
Chip M2 Ultra (76c)
Memory 192 GB
GPU Cores 76
Software
oMLX v0.2.6
macOS macOS 26.3
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 317.9 28.2 105.3 GB view
8k 305.9 22.6 106.8 GB view
16k 259.9 18.2 108.2 GB current
Batching Results
Batch Size TG tok/s Speedup
28.2 1.00×
40.3 1.43×
50.8 1.80×