← Back to community benchmarks

gemma-4-26b-a4b-it

M4 Pro (20c) · 48 GB · 4bit · 2026-04-07
Performance
32k
tokens
620.8
PP tok/s
24.1
TG tok/s
52780
TTFT (ms)
16.0
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 48 GB
GPU Cores 20
Software
oMLX v0.3.4
macOS macOS 26.4
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 692.1 65.5 14.2 GB view
4k 744.6 60.9 14.7 GB view
8k 739.6 53.6 14.8 GB view
16k 704.9 37.9 15.2 GB view
32k 620.8 24.1 16.0 GB current
Batching Results
Batch Size TG tok/s Speedup
65.5 1.00×
95.1 1.45×
115.8 1.77×