← Back to community benchmarks

gemma-4-31b-it

M3 Ultra (60c) · 256 GB · 8bit · 2026-05-27
Performance
16k
tokens
240.1
PP tok/s
16.3
TG tok/s
68249
TTFT (ms)
36.9
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
Software
oMLX v0.3.11
macOS macOS 26.5
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 246.4 18.3 31.8 GB view
4k 252.8 17.8 34.5 GB view
8k 249.8 17.3 35.0 GB view
16k 240.1 16.3 36.9 GB current
32k 222.3 14.6 39.0 GB view
64k 193.2 12.1 45.8 GB view
128k 150.0 8.1 57.9 GB view
Batching Results
Batch Size TG tok/s Speedup
18.3 1.00×
30.1 1.64×
32.0 1.75×