← Back to community benchmarks

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

M2 Max (30c) · 32 GB · 3bit · 2026-05-07
Performance
32k
tokens
591.6
PP tok/s
40.1
TG tok/s
55387
TTFT (ms)
13.7
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 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
8k 767.5 57.4 12.0 GB view
16k 674.6 52.8 12.4 GB view
32k 591.6 40.1 13.7 GB current
64k 471.7 25.8 14.8 GB view