← Back to community benchmarks

gemma-4-26B-A4B-it

M5 Pro (20c) · 64 GB · 4bit · 2026-05-16
Performance
128k
tokens
836.0
PP tok/s
20.6
TG tok/s
156791
TTFT (ms)
22.7
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.3.9.dev2
macOS macOS 26.5
Context 131,072
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
32k 1,802 50.5 16.0 GB view
64k 1,375 37.0 18.5 GB view
128k 836.0 20.6 22.7 GB current