← Back to community benchmarks

gemma-4-26B-A4B-it-oQ3

M2 Max (30c) · 32 GB · 3bit · 2026-05-07
Performance
8k
tokens
692.2
PP tok/s
54.8
TG tok/s
11835
TTFT (ms)
12.1
Peak mem (GB)
Hardware
Chip M2 Max (30c)
Memory 32 GB
GPU Cores 30
Software
oMLX v0.3.8
macOS macOS 26.3.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
8k 692.2 54.8 12.1 GB current
16k 611.6 45.2 12.9 GB view
32k 550.3 42.9 13.7 GB view
64k 480.5 31.0 14.8 GB view