← Back to community benchmarks

gemma-4-31b

M2 Ultra (76c) · 192 GB · 4bit · 2026-05-14
Performance
1k
tokens
169.9
PP tok/s
26.1
TG tok/s
6034
TTFT (ms)
17.8
Peak mem (GB)
Hardware
Chip M2 Ultra (76c)
Memory 192 GB
GPU Cores 76
Software
oMLX v0.3.8
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 169.9 26.1 17.8 GB current
4k 179.9 24.8 20.2 GB view
8k 179.5 23.4 20.7 GB view
16k 175.5 20.9 22.1 GB view
32k 167.1 16.8 24.8 GB view
64k 145.2 12.4 31.4 GB view
Batching Results
Batch Size TG tok/s Speedup
26.1 1.00×
33.7 1.29×
68.4 2.62×
137.1 5.25×