← Back to community benchmarks

gemma-4-31B-it-oQ4

M2 Max (38c) · 96 GB · 4bit · 2026-06-04
Performance
32k
tokens
135.6
PP tok/s
11.7
TG tok/s
241571
TTFT (ms)
23.3
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 152.7 15.6 18.1 GB view
4k 151.5 15.1 19.9 GB view
8k 143.7 14.4 20.4 GB view
16k 143.4 13.2 21.1 GB view
32k 135.6 11.7 23.3 GB current
64k 118.7 9.5 28.1 GB view
Batching Results
Batch Size TG tok/s Speedup
15.6 1.00×
21.5 1.38×
24.7 1.58×
49.2 3.15×