← Back to community benchmarks

gemma-4-26B-A4B-it

M4 Pro (20c) · 48 GB · 8bit · 2026-05-12
Performance
16k
tokens
641.0
PP tok/s
38.7
TG tok/s
25562
TTFT (ms)
27.1
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 16,384
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 view
16k 641.0 38.7 27.1 GB current
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×