← Back to community benchmarks

gemma-4-26B-A4B-it

M4 Pro (20c) · 64 GB · 4bit · 2026-05-21
Performance
16k
tokens
659.8
PP tok/s
54.9
TG tok/s
24833
TTFT (ms)
15.6
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.3.8
macOS macOS 26.5
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 674.1 66.8 14.3 GB view
4k 745.6 63.9 14.9 GB view
8k 742.3 60.9 15.1 GB view
16k 659.8 54.9 15.6 GB current
32k 554.5 45.8 16.5 GB view
64k 478.7 36.8 17.7 GB view
Batching Results
Batch Size TG tok/s Speedup
66.8 1.00×
96.9 1.45×
115.7 1.73×
135.3 2.03×