← Back to community benchmarks

gemma-4-26B-A4B-it-oQ8

M4 Max (40c) · 128 GB · 8bit · 2026-06-03
Performance
16k
tokens
1,350
PP tok/s
69.7
TG tok/s
12136
TTFT (ms)
27.1
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 15.7.4
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,164 78.9 25.8 GB view
4k 1,389 76.4 26.3 GB view
8k 1,403 74.3 26.7 GB view
16k 1,350 69.7 27.1 GB current
32k 1,227 62.1 28.0 GB view
64k 1,019 51.0 30.0 GB view