← Back to community benchmarks

gemma-4-26B-A4B-it-oQ4

M4 Max (32c) · 36 GB · 4bit · 2026-05-03
Performance
4k
tokens
1,184
PP tok/s
72.1
TG tok/s
3459
TTFT (ms)
14.9
Peak mem (GB)
Hardware
Chip M4 Max (32c)
Memory 36 GB
GPU Cores 32
Software
oMLX v0.3.6
macOS macOS 26.4
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,034 85.4 14.4 GB view
4k 1,184 72.1 14.9 GB current