← Back to community benchmarks

gemma-4-31B-it-qat-OptiQ

M3 Ultra (60c) · 256 GB · 4bit · 2026-07-22
Performance
32k
tokens
220.1
PP tok/s
19.9
TG tok/s
148889
TTFT (ms)
27.6
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
Software
oMLX v0.5.3
macOS macOS 26.5.2
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 268.7 25.4 22.3 GB view
4k 255.5 24.5 24.1 GB view
8k 246.7 24.0 24.4 GB view
16k 235.7 22.2 25.2 GB view
32k 220.1 19.9 27.6 GB current
64k 181.1 15.7 32.8 GB view