← Back to community benchmarks

gemma-4-31b-5bit

M4 Max (40c) · 64 GB · 5bit · 2026-05-06
Performance
16k
tokens
175.4
PP tok/s
17.4
TG tok/s
93389
TTFT (ms)
25.4
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.9.dev1
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 190.9 19.8 21.4 GB view
4k 188.6 19.0 23.8 GB view
8k 181.5 18.5 24.3 GB view
16k 175.4 17.4 25.4 GB current
32k 159.5 13.6 28.4 GB view
64k 133.6 11.5 34.4 GB view
Batching Results
Batch Size TG tok/s Speedup
19.8 1.00×
16.6 0.84×
24.3 1.23×
26.5 1.34×