← Back to community benchmarks

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

M1 Max (32c) · 32 GB · 3bit · 2026-05-03
Performance
1k
tokens
619.8
PP tok/s
52.9
TG tok/s
1652
TTFT (ms)
11.4
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 32 GB
GPU Cores 32
Software
oMLX v0.3.8
macOS macOS 15.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 619.8 52.9 11.4 GB current
4k 738.2 51.6 11.9 GB view
8k 664.9 48.6 12.3 GB view