← Back to community benchmarks

gemma-4-26b-a4b-it

M4 Pro (16c) · 24 GB · 4bit · 2026-06-03
Performance
32k
tokens
510.7
PP tok/s
47.7
TG tok/s
64164
TTFT (ms)
16.3
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 24 GB
GPU Cores 16
Software
oMLX v0.4.0
macOS macOS 26.5
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 568.4 64.2 14.3 GB view
4k 602.1 62.1 14.9 GB view
32k 510.7 47.7 16.3 GB current
64k 420.0 36.1 18.5 GB view
Batching Results
Batch Size TG tok/s Speedup
64.2 1.00×
84.0 1.31×
96.3 1.50×