← Back to community benchmarks

gemma-4-31b-it

M5 Max (40c) · 128 GB · 4bit · 2026-05-01
Performance
8k
tokens
176.3
PP tok/s
16.8
TG tok/s
46454
TTFT (ms)
19.6
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.8rc1
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 208.3 26.1 17.6 GB view
4k 193.4 23.9 19.3 GB view
8k 176.3 16.8 19.6 GB current
16k 120.6 13.6 20.4 GB view
Batching Results
Batch Size TG tok/s Speedup
26.1 1.00×
23.9 0.92×