← Back to community benchmarks

gemma-4-26b-a4b-it

M4 Pro (20c) · 64 GB · 8bit · 2026-05-22
Performance
32k
tokens
584.9
PP tok/s
36.4
TG tok/s
56022
TTFT (ms)
27.8
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.3.9
macOS macOS 26.3
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 668.0 45.1 25.8 GB view
4k 726.4 42.9 26.4 GB view
8k 723.6 42.1 26.6 GB view
32k 584.9 36.4 27.8 GB current
64k 482.9 29.4 30.2 GB view
Batching Results
Batch Size TG tok/s Speedup
45.1 1.00×
66.4 1.47×
82.6 1.83×