← Back to community benchmarks

gemma-4-26b-a4b-it

M4 Pro (20c) · 24 GB · 4bit · 2026-05-18
Performance
16k
tokens
655.1
PP tok/s
42.6
TG tok/s
25011
TTFT (ms)
15.6
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 24 GB
GPU Cores 20
Software
oMLX v0.3.9.dev2
macOS macOS 15.7.3
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 676.8 66.3 14.3 GB view
4k 732.9 63.8 15.0 GB view
8k 721.6 59.8 15.3 GB view
16k 655.1 42.6 15.6 GB current