← Back to community benchmarks

gemma-4-26b-a4b-it

M3 Pro (14c) · 36 GB · 4bit · 2026-05-22
Performance
8k
tokens
456.8
PP tok/s
38.0
TG tok/s
17934
TTFT (ms)
15.1
Peak mem (GB)
Hardware
Chip M3 Pro (14c)
Memory 36 GB
GPU Cores 14
Software
oMLX v0.3.9
macOS macOS 26.5
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 426.6 40.8 14.3 GB view
4k 446.3 37.9 14.9 GB view
8k 456.8 38.0 15.1 GB current
16k 432.6 34.5 15.6 GB view
32k 385.2 27.7 16.5 GB view
64k 310.0 15.6 18.7 GB view