ANVE: the private AI office, on the record. See what that means
ANVERun it on your own hardware · updated 2026-10-16
Short answer. distil-large-v3 needs about 1.9 GB of memory at 4-bit, 2.3 GB at 8-bit and 3.0 GB at full 16-bit precision, including runtime overhead. It has about 756 million parameters. Licence in short: commercial use allowed. 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.
distil-large-v3 is a speech-recognition model that turns recorded speech into text, published by Hugging Face (Distil-Whisper) on Hugging Face on 21 March 2024. It has about 756 million parameters.
Its card lists the licence as MIT. In short, the licence allows commercial use, modification and redistribution as long as the copyright notice is kept.
Hugging Face counted about 551,158 downloads of it in the 30 days before we checked (7 Oct 2026), and 383 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.
Speech models also need working memory for the audio being processed, which is small next to the weights.
| Precision | Weights | Total, estimated |
|---|---|---|
| BF16 (full precision) | 1.5 GB | 3.0 GB |
| 8-bit (Q8_0) | 0.80 GB | 2.3 GB |
| 4-bit (Q4_K) | 0.43 GB | 1.9 GB |
| Setting | Value in config.json |
|---|---|
| Architecture class | WhisperForConditionalGeneration |
| Model type | whisper |
| Layers | 32 |
| Vocabulary | 51,866 |
| Stored precision | float16 |
How the verdicts are worked out: on ANVE One, about three quarters of 64 GB of unified memory is available to the model; on ANVE Office and ANVE Office Pro, the model has to fit in the 24 GB on the graphics card, with 64 GB or 128 GB of system memory for everything else. This is arithmetic against the launch specification, not a test. 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 the model that turns a recorded meeting or call into a transcript. Accuracy depends heavily on the language, the microphone and how people talk over each other, so test it on your own recordings.
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.