← Back to community benchmarks

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

M1 Pro (16c) · 32 GB · 4bit · 2026-05-28
Performance
64k
tokens
192.7
PP tok/s
14.2
TG tok/s
340116
TTFT (ms)
17.8
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 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 229.7 33.3 14.7 GB view
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 current
Batching Results
Batch Size TG tok/s Speedup
33.3 1.00×
41.5 1.25×
46.2 1.39×