← Back to community benchmarks

gemma-4-26b-a4b-it

M1 Max (24c) · 32 GB · 4bit · 2026-04-05
Performance
32k
tokens
346.3
PP tok/s
10.6
TG tok/s
94628
TTFT (ms)
17.1
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 32 GB
GPU Cores 24
Software
oMLX v0.3.1
macOS macOS 26.4
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
8k 380.2 25.7 15.9 GB view
16k 374.7 19.6 16.3 GB view
32k 346.3 10.6 17.1 GB current
64k 295.5 5.8 18.8 GB view