← Back to community benchmarks

gemma-4-26b-a4b-it

M5 Max (40c) · 128 GB · 8bit · 2026-04-03
Performance
16k
tokens
2,202
PP tok/s
47.3
TG tok/s
7441
TTFT (ms)
27.8
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.1
macOS macOS 26.4
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,958 64.0 26.8 GB view
4k 3,322 61.3 27.1 GB view
16k 2,202 47.3 27.8 GB current
32k 2,038 37.6 28.6 GB view
64k 1,715 24.2 30.3 GB view
128k 1,192 12.5 33.9 GB view