← Back to community benchmarks

gemma-4-26b-a4b-it

M1 Max (24c) · 32 GB · 4bit · 2026-04-05
Performance
8k
tokens
380.2
PP tok/s
25.7
TG tok/s
21544
TTFT (ms)
15.9
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 32 GB
GPU Cores 24
Software
oMLX v0.3.1
macOS macOS 26.4
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
8k 380.2 25.7 15.9 GB current
16k 374.7 19.6 16.3 GB view
32k 346.3 10.6 17.1 GB view
64k 295.5 5.8 18.8 GB view