← Back to community benchmarks

gemma-4-26b-a4b-it

M5 Pro (16c) · 48 GB · 4bit · 2026-04-03
Performance
16k
tokens
1,730
PP tok/s
42.6
TG tok/s
9471
TTFT (ms)
15.3
Peak mem (GB)
Hardware
Chip M5 Pro (16c)
Memory 48 GB
GPU Cores 16
Software
oMLX v0.3.2
macOS macOS 26.3.2
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,399 61.2 14.3 GB view
4k 1,642 58.6 14.8 GB view
8k 1,820 54.1 14.9 GB view
16k 1,730 42.6 15.3 GB current
Batching Results
Batch Size TG tok/s Speedup
61.2 1.00×
78.2 1.28×
99.1 1.62×