← Back to community benchmarks

gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-qx86-hi

M3 Ultra (60c) · 256 GB · 8bit · 2026-05-04
Performance
1k
tokens
246.6
PP tok/s
20.0
TG tok/s
4152
TTFT (ms)
28.4
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
Software
oMLX v0.3.7
macOS macOS 26.2
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 246.6 20.0 28.4 GB current
4k 250.7 19.1 30.2 GB view
8k 248.1 5.4 31.5 GB view
16k 203.7 7.2 35.2 GB view
Batching Results
Batch Size TG tok/s Speedup
20.0 1.00×
19.3 0.97×
26.3 1.31×
93.7 4.69×