← Back to community benchmarks

gemma-4-31B-it

M2 Max (38c) · 64 GB · 8bit · 2026-05-15
Performance
64k
tokens
75.8
PP tok/s
7.0
TG tok/s
864348
TTFT (ms)
45.8
Peak mem (GB)
Hardware
Chip M2 Max (38c)
Memory 64 GB
GPU Cores 38
Software
oMLX v0.3.9.dev2
macOS macOS 26.5
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 94.1 9.9 31.8 GB view
4k 94.6 9.9 34.5 GB view
8k 94.2 9.7 35.0 GB view
16k 92.0 9.1 36.1 GB view
32k 83.7 8.2 39.2 GB view
64k 75.8 7.0 45.8 GB current
Batching Results
Batch Size TG tok/s Speedup
9.9 1.00×
17.9 1.81×
22.2 2.24×
19.0 1.92×