Qwen3.6-35B-A3B
The memory it needs, what you may do with it, and the hardware it suits.

Qwen3.6-35B-A3B is a vision-language model: it reads images (scanned pages, photos, charts and screenshots) as well as text, published by Alibaba’s Qwen team on Hugging Face on 15 April 2026. It has about 36 billion parameters and a configured context window of 262,144 tokens. It is a mixture-of-experts model: 256 experts, 8 used for each token, so only about 3B parameters are active at a time.

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 3,524,086 downloads of it in the 30 days before we checked (7 Oct 2026), and 2,940 people have liked it there.

We size it the way you would size any model: the weights (parameters × bits ÷ 8), the KV cache for 8,192 tokens of context, and roughly 1.5 GB for the runtime itself. Real use varies with settings.

Each token of context adds about 0.02 MB of KV cache at 16-bit, so 32,768 tokens would add about 0.67 GB. Only 10 of its 40 layers use standard attention; the others keep a small fixed state, so the cache is smaller than in a classic transformer.

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.

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.

• Qwen3.5-35B-A3B: a variant with the same size and memory needs (same parameter count, so the memory figures above apply).

• gemma-4-31B-it (31.3B parameters, about 19 GB at 4-bit before context; commercial use allowed)
• medgemma-27b-it (28.8B parameters, about 18 GB at 4-bit before context; custom licence: check before commercial use)
• gemma-3-27b-it (27.4B parameters, about 17 GB at 4-bit before context; commercial use allowed, with conditions)

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.