← Back to community benchmarks

gemma-4-26B-A4B-it

M4 Pro (20c) · 64 GB · 6bit · 2026-05-18
Performance
1k
tokens
641.8
PP tok/s
52.2
TG tok/s
1596
TTFT (ms)
20.3
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.3.9.dev2
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 641.8 52.2 20.3 GB current
4k 667.7 49.4 21.0 GB view
8k 621.7 46.5 21.1 GB view
Batching Results
Batch Size TG tok/s Speedup
52.2 1.00×
71.0 1.36×