← Back to community benchmarks

gemma-4-26b-a4b-it

M5 (10c) · 32 GB · 4bit · 2026-05-14
Performance
32k
tokens
520.2
PP tok/s
20.1
TG tok/s
62987
TTFT (ms)
16.3
Peak mem (GB)
Hardware
Chip M5 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.3.9.dev2
macOS macOS 26.5
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 526.7 30.5 14.2 GB view
8k 608.7 27.7 14.9 GB view
32k 520.2 20.1 16.3 GB current
64k 350.0 11.5 18.5 GB view