← Back to community benchmarks

gemma-4-26B-A4B-it

M2 Pro (19c) · 32 GB · 4bit · 2026-05-26
Performance
8k
tokens
321.6
PP tok/s
41.0
TG tok/s
25471
TTFT (ms)
14.8
Peak mem (GB)
Hardware
Chip M2 Pro (19c)
Memory 32 GB
GPU Cores 19
Software
oMLX v0.3.10
macOS macOS 26.5
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 300.5 44.7 14.3 GB view
4k 322.7 43.1 14.6 GB view
8k 321.6 41.0 14.8 GB current
16k 312.3 37.3 15.2 GB view
32k 291.0 32.1 16.0 GB view
64k 253.3 24.5 17.7 GB view