← Back to community benchmarks

Gemma-4-21B-REAP-JANG3M

M3 Ultra (60c) · 96 GB · unknown · 2026-05-28
Performance
4k
tokens
1,735
PP tok/s
88.0
TG tok/s
2361
TTFT (ms)
10.9
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 96 GB
GPU Cores 60
Software
oMLX v0.3.12
macOS macOS 26.5
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,339 89.5 10.2 GB view
4k 1,735 88.0 10.9 GB current
8k 1,793 82.6 11.0 GB view
16k 1,710 77.7 11.5 GB view
32k 1,518 66.7 12.4 GB view
64k 1,220 47.0 14.5 GB view
128k 852.4 29.7 18.6 GB view
195k 626.2 22.2 23.6 GB view
Batching Results
Batch Size TG tok/s Speedup
89.5 1.00×
133.4 1.49×
199.8 2.23×
249.3 2.79×