← Back to community benchmarks

gemma-4-26b-a4b-it

M4 Pro (16c) · 24 GB · 4bit · 2026-04-28
Performance
32k
tokens
510.8
PP tok/s
26.9
TG tok/s
64155
TTFT (ms)
15.3
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 24 GB
GPU Cores 16
Software
oMLX v0.3.8rc1
macOS macOS 26.5
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 569.8 65.7 13.6 GB view
4k 601.3 60.8 14.0 GB view
8k 594.6 50.1 14.1 GB view
16k 569.3 40.0 14.5 GB view
32k 510.8 26.9 15.3 GB current
64k 425.9 12.1 17.0 GB view
Batching Results
Batch Size TG tok/s Speedup
65.7 1.00×
85.4 1.30×
98.9 1.51×