← Back to community benchmarks

gemma-4-26b-a4b-it

M3 Pro (18c) · 36 GB · 4bit · 2026-05-09
Performance
32k
tokens
482.9
PP tok/s
32.4
TG tok/s
67863
TTFT (ms)
16.5
Peak mem (GB)
Hardware
Chip M3 Pro (18c)
Memory 36 GB
GPU Cores 18
Software
oMLX v0.3.9.dev1
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
8k 567.7 40.1 14.8 GB view
16k 539.9 36.8 15.6 GB view
32k 482.9 32.4 16.5 GB current
64k 373.9 23.4 18.5 GB view