← Back to community benchmarks

gemma-4-26b-a4b-it

M5 Max (40c) · 128 GB · 8bit · 2026-05-04
Performance
32k
tokens
2,615
PP tok/s
64.8
TG tok/s
12531
TTFT (ms)
27.5
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 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
1k 1,690 85.4 25.8 GB view
4k 2,213 82.7 26.4 GB view
8k 2,745 80.2 26.6 GB view
16k 2,814 74.4 27.1 GB view
32k 2,615 64.8 27.5 GB current
64k 2,120 49.5 29.2 GB view
128k 1,444 33.5 32.7 GB view