← Back to community benchmarks

gemma-4-26B-A4B-it

M4 Pro (20c) · 48 GB · 8bit · 2026-05-12
Performance
8k
tokens
718.2
PP tok/s
42.3
TG tok/s
11406
TTFT (ms)
26.6
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 48 GB
GPU Cores 20
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 614.4 45.1 25.8 GB view
4k 699.7 43.9 26.4 GB view
8k 718.2 42.3 26.6 GB current
16k 641.0 38.7 27.1 GB view
32k 574.0 35.5 28.0 GB view
64k 493.0 29.1 29.2 GB view
Batching Results
Batch Size TG tok/s Speedup
45.1 1.00×
66.5 1.47×
84.6 1.88×