← Back to community benchmarks

gemma-4-26B-A4B-it

M5 Pro (20c) · 64 GB · 4bit · 2026-04-02
Performance
8k
tokens
2,338
PP tok/s
57.7
TG tok/s
3504
TTFT (ms)
16.3
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.3.1
macOS macOS 26.4
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,279 62.4 15.1 GB view
4k 2,386 59.9 15.9 GB view
8k 2,338 57.7 16.3 GB current
16k 2,194 52.5 16.9 GB view
Batching Results
Batch Size TG tok/s Speedup
62.4 1.00×
73.3 1.17×
108.1 1.73×