← Back to community benchmarks

gemma-4-31b-it-mxfp8

M3 Ultra (60c) · 256 GB · 8bit · 2026-05-10
Performance
195k
tokens
123.0
PP tok/s
7.5
TG tok/s
1626532
TTFT (ms)
71.3
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
Software
oMLX v0.3.9.dev1
macOS macOS 26.4.1
Context 200,000
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 245.7 18.3 30.9 GB view
4k 249.1 17.9 33.6 GB view
8k 247.3 17.5 34.1 GB view
16k 239.1 16.7 35.5 GB view
32k 223.3 15.2 38.3 GB view
64k 195.1 12.9 44.9 GB view
128k 152.1 9.1 56.2 GB view
195k 123.0 7.5 71.3 GB current
Batching Results
Batch Size TG tok/s Speedup
18.3 1.00×
24.3 1.33×
26.6 1.45×
53.2 2.91×