← Back to community benchmarks

gemma-4-26B-A4B-it-QAT

M5 Max (40c) · 128 GB · 4bit · 2026-07-23
Performance
8k
tokens
4,110
PP tok/s
99.3
TG tok/s
1993
TTFT (ms)
15.2
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.5.3
macOS macOS 26.5.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
8k 4,110 99.3 15.2 GB current
64k 2,592 61.5 27.2 GB view