Ollama QAT Weights Put Claimed Gemma 4 31B Scores Near Claude Opus 4

The report says Google's 31B model can run on consumer laptop hardware, with a smaller E4B variant claimed to fit a 2GB phone.

By · Published · Updated

Primary source: Aligned News - AI Intelligence

Why it matters

If the claim holds up, Ollama's QAT weights would strengthen the case for running capable AI on ordinary devices, pressuring cloud-only model economics.

Illustration of an Ollama QAT-weighted Gemma 4 31B model architecture diagram labeled with a smaller E4B phone-sized variant and a comparison note to Claude Opus 4.

Google (@Google)'s Gemma 4 31B is being described as a local-inference milestone after an Aligned News post on X said the model benchmarks near Anthropic's Claude Opus 4 while running on consumer laptop hardware through Ollama's new QAT weights.

https://x.com/itsPaulAi/status/2062973423303712949…

When you purchase through links in our articles, we may earn a small commission. This doesn’t affect our editorial independence.

Reader comments

Conversation for this story loads after sign-in.