← Back to community benchmarks

gemma-4-31B-it-oQ4

M4 Max (40c) · 128 GB · 4bit · 2026-05-08
Performance
32k
tokens
178.9
PP tok/s
18.7
TG tok/s
183198
TTFT (ms)
25.4
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.9.dev1
macOS macOS 15.7.4
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 199.1 23.4 18.1 GB view
4k 200.8 22.8 20.3 GB view
8k 197.9 22.1 22.6 GB view
16k 191.1 20.7 23.8 GB view
32k 178.9 18.7 25.4 GB current
64k 157.8 15.5 31.4 GB view
128k 123.4 11.6 43.4 GB view
Batching Results
Batch Size TG tok/s Speedup
23.4 1.00×
37.6 1.61×
42.2 1.80×