Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

Gemma 3 270M Runs Inside a Ricoh Laser Printer

AI summary

Google DeepMind engineer Omar Sanseviero demonstrated that a quantized Gemma 3 270M model could run inside a Ricoh laser printer through its PostScript Level 3 interpreter, without changing firmware or adding external compute hardware. Carbon executed 18 transformer layers while dynamic layer streaming kept peak memory use at about 14.1MB, and the printer produced the response “Read the fine print.” Reports conflict over throughput: Wccftech and cnBeta cite 61.3 tokens per second, while IT之家 AI describes roughly 60 seconds per generated token.

In-depth insight

The experiment, as reported by Wccftech, IT之家 AI and cnBeta, demonstrates that a quantized small language model can perform inference through an ordinary printer’s PostScript environment under severe memory constraints.

AIHardware

Google DeepMind Engineer Successfully Fires Up Gemma 3 With 270-Million-Parameters On An Office Laser Printer While Only Having 14MB RAM At His Disposal

Omar Sohail•Nov 19, 2026 at 10:49am EST

9 Comments

Who says you only need GPUs to run AI models? / Image enhanced using Google Gemini

Add Wccftech on Google:

Some source content is omitted. Continue reading on the original site.

#Gemma 3 270M#Carbon#Ricoh#Google DeepMind#PostScript#Omar Sanseviero

Original · 4 min readRead the original
Group chat

No comments yet. Start the conversation.