← Back to community benchmarks

gemma-4-31b-it-oQ4

M5 Max (40c) · 128 GB · 4bit · 2026-05-02
Performance
128k
tokens
270.7
PP tok/s
7.8
TG tok/s
484205
TTFT (ms)
43.4
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 131,072
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 670.6 25.7 18.1 GB view
64k 468.3 13.5 28.0 GB view
128k 270.7 7.8 43.4 GB current
Batching Results
Batch Size TG tok/s Speedup
25.7 1.00×
27.8 1.08×
74.5 2.90×