← Back to community benchmarks

gemma-4-31B-it-oQ4

M2 Max (38c) · 96 GB · 4bit · 2026-06-04
Performance
32k
tokens
134.0
PP tok/s
10.6
TG tok/s
244626
TTFT (ms)
23.4
Peak mem (GB)
Hardware
Chip M2 Max (38c)
Memory 96 GB
GPU Cores 38
Software
oMLX v0.4.1
macOS macOS 15.7.5
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 151.5 14.7 18.1 GB view
4k 152.7 14.4 19.9 GB view
8k 145.6 14.0 20.4 GB view
16k 144.3 12.7 21.0 GB view
32k 134.0 10.6 23.4 GB current
64k 117.4 8.9 28.0 GB view
Batching Results
Batch Size TG tok/s Speedup
14.7 1.00×
20.3 1.38×
22.6 1.54×
44.3 3.01×