gemma-3-27b-it
Memory at each precision, the licence in plain words, and where it fits.

gemma-3-27b-it is a vision-language model: it reads images (scanned pages, photos, charts and screenshots) as well as text, published by Google on Hugging Face on 1 March 2025. It has about 27.4 billion parameters and a configured context window of 131,072 tokens.

Its card lists the licence as Gemma Terms of Use. In short, the licence allow commercial use, subject to Google’s prohibited use policy, and require the terms to be passed on with the model. Access on Hugging Face requires accepting the publisher’s terms first.

Hugging Face counted about 417,368 downloads of it in the 30 days before we checked (7 Oct 2026), and 2,046 people have liked it there.

It is built on google/gemma-3-27b-pt, according to its card.

The arithmetic: parameters × bits per weight ÷ 8 gives the weights; add the KV cache, which grows with every token of context; then add about 1.5 GB for the runtime. These are estimates for planning, not measurements.

Each token of context adds about 0.51 MB of KV cache at 16-bit, so 32,768 tokens would add about 17 GB. Some layers use sliding-window attention, so the real cache is smaller than this full-attention estimate.

These verdicts are arithmetic, not tests, against the specification at launch: ANVE One can give a model about three quarters of its 64 GB of unified memory, while ANVE Office and ANVE Office Pro hold it on a 24 GB graphics card and keep the rest of the stack in 64 GB or 128 GB of system memory. ANVE’s tested default is Qwen 3.8 27B; this model is not yet validated on ANVE.

This is the class ANVE runs by default (27B-class): strong enough for meeting minutes, summaries, drafting and question answering over an office’s own documents, and small enough for one box.

• Qwen3.8-27B (27.8B parameters, about 17 GB at 4-bit before context; commercial use allowed)
• Qwen3.6-27B (27.8B parameters, about 17 GB at 4-bit before context; commercial use allowed)
• Qwen3-VL-30B-A3B-Instruct (31.1B parameters, about 19 GB at 4-bit before context; commercial use allowed)

No sealed ANVE unit exists; every image of the appliance on this site is a labelled render. The software runs today on a development machine. No customers yet, no certifications, no delivery date, and the final price is not announced.

Reservations are ₹999 in India or US$12 elsewhere, refundable in full until you confirm an order in writing (terms). Offices that cannot use cloud AI can apply to be one of ten design partners.