ANVE: the private AI office, on the record. See what that means

ANVE

Run it on your own hardware · updated 2026-10-16

gemma-4-31B-it
Memory at each precision, the licence in plain words, and where it fits.

Short answer. gemma-4-31B-it needs about 20 GB of memory at 4-bit, 36 GB at 8-bit and 65 GB at full 16-bit precision, including runtime overhead and an 8,192-token KV cache. It has about 31.3 billion parameters and a 262,144-token context window. Licence in short: commercial use allowed. By memory alone, on ANVE’s launch configurations: ANVE One fits at 8-bit, ANVE Office fits at 4-bit, ANVE Office Pro (GPU) fits at 4-bit. These are estimates from its published size, not benchmarks.

01

What it is

gemma-4-31B-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 11 March 2026. It has about 31.3 billion parameters and a configured context window of 262,144 tokens.

Its card lists the licence as Apache 2.0. In short, the licence allows commercial use, modification and redistribution, with attribution and a copy of the licence, and includes a patent grant.

Hugging Face counted about 9,585,344 downloads of it in the 30 days before we checked (7 Oct 2026), and 4,046 people have liked it there.

It is built on google/gemma-4-31B, according to its card.

02

How much memory it needs

How these figures are worked out: weights = parameters × bits per weight ÷ 8. The KV cache is added for 8,192 tokens of context, plus about 1.5 GB of runtime overhead. Treat the totals as planning estimates.

Each token of context adds about 0.16 MB of KV cache at 16-bit, so 32,768 tokens would add about 5.4 GB. 50 of its 60 layers use sliding-window attention, so the real cache is smaller than this full-attention estimate.

PrecisionWeightsKV cache (8,192 tokens)Total, estimated
BF16 (full precision)63 GB1.3 GB65 GB
8-bit (Q8_0)33 GB1.3 GB36 GB
4-bit (Q4_K)18 GB1.3 GB20 GB
03

Architecture at a glance

SettingValue in config.json
Architecture classGemma4ForConditionalGeneration
Model typegemma4
Layers60
Hidden size5,376
Attention heads32
Key-value heads16 (grouped-query attention)
Head size256
Vocabulary262,144
Configured context262,144
Stored precisionbfloat16
04

Will it fit on ANVE?

Arithmetic against the launch specification, not a test: about three quarters of ANVE One’s 64 GB of unified memory for the model (as AMD’s Variable Graphics Memory allows), and the 24 GB on the graphics card in ANVE Office and ANVE Office Pro, which keep the rest of the stack in 64 GB and 128 GB of system memory. ANVE’s tested default is Qwen 3.8 27B; this model is not yet validated on ANVE.

Configuration (at launch)Memory for the modelVerdict
ANVE Oneabout 48 GB of 64 GB unified memoryfits at 8-bit
ANVE Office24 GB on the RTX PRO 4000 Blackwell SFF Editionfits at 4-bit
ANVE Office Pro (GPU)24 GB on the RTX PRO 4000 Blackwellfits at 4-bit
05

What an office would use it for

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.

06

Similar models to compare

  • Qwen3-VL-30B-A3B-Instruct (31.1B parameters, about 19 GB at 4-bit before context; commercial use allowed)
  • Qwen3-VL-32B-Instruct (33.4B parameters, about 20 GB at 4-bit before context; commercial use allowed)
  • Qwen2.5-VL-32B-Instruct (33.5B parameters, about 20 GB at 4-bit before context; commercial use allowed)
07

Questions people ask

How much memory does gemma-4-31B-it need?
About 20 GB at 4-bit, 36 GB at 8-bit and 65 GB at full 16-bit precision, including an 8,192-token KV cache and about 1.5 GB of runtime overhead. These are estimates from its parameter count.
Can gemma-4-31B-it run on a 24 GB graphics card?
Yes, at 4-bit by this estimate, with room left for context.
Is gemma-4-31B-it free for commercial use?
Its card lists Apache 2.0, which allows commercial use, modification and redistribution, with attribution and a copy of the licence, and includes a patent grant. Read the licence itself before relying on this summary; it is not legal advice.
What is gemma-4-31B-it’s context window?
Its configuration sets 262,144 tokens. Longer contexts need more memory for the KV cache, so the practical limit on a given machine can be lower.
08

What is not real yet

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.