← Back to community benchmarks

gemma-4-26b-a4b-it

M4 Max (40c) · 128 GB · 8bit · 2026-04-13
Performance
8k
tokens
1,252
PP tok/s
61.0
TG tok/s
6546
TTFT (ms)
26.9
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.5.dev1
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,167 67.3 26.4 GB view
4k 1,375 66.3 26.9 GB view
8k 1,252 61.0 26.9 GB current
16k 1,084 52.2 27.3 GB view