← Back to community benchmarks

gemma-4-31B-it

M4 Max (40c) · 128 GB · unknown · 2026-05-19
Performance
32k
tokens
195.1
PP tok/s
7.0
TG tok/s
167949
TTFT (ms)
65.8
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.9rc1
macOS macOS 26.4
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 214.7 7.6 58.5 GB view
4k 219.4 7.6 61.2 GB view
16k 211.6 7.3 62.5 GB view
32k 195.1 7.0 65.8 GB current
64k 164.5 6.4 71.8 GB view
Batching Results
Batch Size TG tok/s Speedup
7.6 1.00×
7.4 0.97×
14.6 1.92×
27.4 3.61×