← Back to community benchmarks

gemma-4-26b-a4b-it-UD

M1 Pro (16c) · 32 GB · 4bit · 2026-05-28
Performance
1k
tokens
229.7
PP tok/s
33.3
TG tok/s
4458
TTFT (ms)
14.7
Peak mem (GB)
Hardware
Chip M1 Pro (16c)
Memory 32 GB
GPU Cores 16
Software
oMLX v0.3.12
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 229.7 33.3 14.7 GB current
16k 244.5 27.6 15.9 GB view
32k 223.5 19.9 16.9 GB view
64k 192.7 14.2 17.8 GB view
Batching Results
Batch Size TG tok/s Speedup
33.3 1.00×
41.5 1.25×
46.2 1.39×