← Back to community benchmarks

gemma-4-26B-A4B-it

M3 Ultra (60c) · 256 GB · 8bit · 2026-05-17
Performance
32k
tokens
1,481
PP tok/s
60.6
TG tok/s
22123
TTFT (ms)
28.0
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
Software
oMLX v0.3.9.dev2
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,344 84.5 25.8 GB view
4k 1,663 81.0 26.5 GB view
8k 1,707 77.5 26.6 GB view
16k 1,649 71.7 27.1 GB view
32k 1,481 60.6 28.0 GB current
64k 1,213 46.1 30.0 GB view
Batching Results
Batch Size TG tok/s Speedup
84.5 1.00×
125.2 1.48×
168.1 1.99×
235.0 2.78×