← Back to community benchmarks

gemma-4-26b-a4b-it

M4 Pro (20c) · 48 GB · 8bit · 2026-05-11
Performance
1k
tokens
673.8
PP tok/s
45.7
TG tok/s
1520
TTFT (ms)
25.8
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 48 GB
GPU Cores 20
Software
oMLX v0.3.9.dev1
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 673.8 45.7 25.8 GB current
4k 731.3 44.8 26.4 GB view
64k 519.4 31.5 29.2 GB view
128k 381.7 23.3 34.2 GB view
Batching Results
Batch Size TG tok/s Speedup
45.7 1.00×
61.1 1.34×
76.1 1.67×