← Back to community benchmarks

gemma-4-26B-A4B-it-OptiQ

M4 Max (40c) · 64 GB · 4bit · 2026-05-27
Performance
32k
tokens
1,154
PP tok/s
59.0
TG tok/s
28390
TTFT (ms)
19.4
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.11
macOS macOS 26.3.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
16k 1,275 71.7 18.1 GB view
32k 1,154 59.0 19.4 GB current
64k 937.9 48.2 21.4 GB view