← Back to community benchmarks

gemma-4-26B-A4B-it

M2 Max (38c) · 32 GB · 4bit · 2026-05-12
Performance
16k
tokens
613.0
PP tok/s
56.8
TG tok/s
26730
TTFT (ms)
15.6
Peak mem (GB)
Hardware
Chip M2 Max (38c)
Memory 32 GB
GPU Cores 38
Software
oMLX v0.3.9.dev2
macOS macOS 26.5
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 559.7 70.7 14.3 GB view
4k 619.7 66.9 14.9 GB view
8k 626.3 54.1 15.1 GB view
16k 613.0 56.8 15.6 GB current
32k 570.7 46.8 16.5 GB view
64k 500.6 35.8 18.5 GB view