ANVE: the private AI office, on the record. See what that means
ANVERun it on your own hardware · updated 2026-10-16
Short answer. Nemotron-Parse-v1.1 needs about 2.0 GB of memory at 4-bit, 2.5 GB at 8-bit and 3.4 GB at full 16-bit precision, including runtime overhead. It has about 957 million parameters. Licence in short: custom licence: check before commercial use. By memory alone, on ANVE’s launch configurations: ANVE One fits at BF16, ANVE Office fits at BF16, ANVE Office Pro (GPU) fits at BF16. These are estimates from its published size, not benchmarks.
Nemotron-Parse-v1.1 is a document-reading model that turns scanned pages and images into text, published by NVIDIA on Hugging Face on 15 November 2025. It has about 957 million parameters.
Its card lists the licence as a custom licence (nvidia-open-model-license). In short, the licence sets its own terms; read it before any commercial use.
Hugging Face counted about 150,622 downloads of it in the 30 days before we checked (7 Oct 2026), and 171 people have liked it there.
The arithmetic: parameters × bits per weight ÷ 8 gives the weights, plus about 1.5 GB for the runtime. These are planning estimates, not measurements.
Inputs are short, so working memory is small next to the weights.
| Precision | Weights | Total, estimated |
|---|---|---|
| BF16 (full precision) | 1.9 GB | 3.4 GB |
| 8-bit (Q8_0) | 1.0 GB | 2.5 GB |
| 4-bit (Q4_K) | 0.54 GB | 2.0 GB |
| Setting | Value in config.json |
|---|---|
| Architecture class | NemotronParseForConditionalGeneration |
| Model type | nemotron_parse |
| Vocabulary | 52,327 |
| Stored precision | bfloat16 |
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.
| Configuration (at launch) | Memory for the model | Verdict |
|---|---|---|
| ANVE One | about 48 GB of 64 GB unified memory | fits at BF16 |
| ANVE Office | 24 GB on the RTX PRO 4000 Blackwell SFF Edition | fits at BF16 |
| ANVE Office Pro (GPU) | 24 GB on the RTX PRO 4000 Blackwell | fits at BF16 |
For an office, this is how scanned invoices, letters and forms become searchable text. Check its output on your own documents, especially tables, stamps and handwriting.
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.