← Back to community benchmarks

gemma-4-26B-A4B-it

M3 Ultra (60c) · 256 GB · 8bit · 2026-05-20
Performance
16k
tokens
1,644
PP tok/s
72.0
TG tok/s
9967
TTFT (ms)
27.1
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
Software
oMLX v0.3.9rc1
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,324 84.5 25.8 GB view
4k 1,654 81.2 26.4 GB view
8k 1,700 77.6 26.6 GB view
16k 1,644 72.0 27.1 GB current
32k 1,481 61.6 28.0 GB view
64k 1,213 46.5 30.0 GB view
Batching Results
Batch Size TG tok/s Speedup
84.5 1.00×
125.6 1.49×
168.1 1.99×
233.2 2.76×