← Back to community benchmarks

gemma-4-31B-it

M5 Max (40c) · 128 GB · 8bit · 2026-05-15
Performance
128k
tokens
198.5
PP tok/s
5.3
TG tok/s
660407
TTFT (ms)
57.1
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 26.4
Context 131,072
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 346.7 12.3 31.8 GB view
4k 418.1 12.1 34.5 GB view
16k 423.7 10.8 35.8 GB view
32k 355.4 8.0 39.1 GB view
64k 266.1 6.5 45.1 GB view
128k 198.5 5.3 57.1 GB current
Batching Results
Batch Size TG tok/s Speedup
12.3 1.00×
16.3 1.33×
22.5 1.83×