← Back to community benchmarks

gemma-4-31b-it

M4 Pro (20c) · 48 GB · 4bit · 2026-04-05
Performance
8k
tokens
96.2
PP tok/s
10.1
TG tok/s
85131
TTFT (ms)
19.6
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 48 GB
GPU Cores 20
Software
oMLX v0.3.4
macOS macOS 26.4
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 101.4 12.5 17.6 GB view
4k 100.4 11.5 19.3 GB view
8k 96.2 10.1 19.6 GB current
16k 91.7 7.8 20.4 GB view
32k 83.5 5.4 22.8 GB view
64k 73.4 3.1 27.6 GB view
Batching Results
Batch Size TG tok/s Speedup
12.5 1.00×
21.5 1.72×
23.6 1.89×