← Back to community benchmarks

gemma-4-31b-5bit

M4 Max (40c) · 64 GB · 5bit · 2026-05-06
Performance
64k
tokens
133.6
PP tok/s
11.5
TG tok/s
490479
TTFT (ms)
34.4
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 65,536
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 view
32k 159.5 13.6 28.4 GB view
64k 133.6 11.5 34.4 GB current
Batching Results
Batch Size TG tok/s Speedup
19.8 1.00×
16.6 0.84×
24.3 1.23×
26.5 1.34×