← Back to community benchmarks

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

M3 Max (40c) · 64 GB · 4bit · 2026-05-05
Performance
32k
tokens
1,072
PP tok/s
60.4
TG tok/s
30558
TTFT (ms)
17.0
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
32k 1,072 60.4 17.0 GB current
64k 856.6 49.2 19.5 GB view