← Back to community benchmarks

gemma-4-26B-A4B-it-oQ6

M3 Max (40c) · 64 GB · 6bit · 2026-05-09
Performance
64k
tokens
769.3
PP tok/s
34.7
TG tok/s
85186
TTFT (ms)
23.7
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 15.7.4
Context 65,536