mms-1b-all
Memory at each precision, the licence in plain words, and where it fits.

mms-1b-all is a speech-recognition model that turns recorded speech into text, published by Meta (FAIR) on Hugging Face on 27 May 2023. It has about 965 million parameters.

Its card lists the licence as CC BY-NC 4.0. In short, the licence allows non-commercial use only, so an office cannot use it for paid client work without a separate licence.

Hugging Face counted about 274,784 downloads of it in the 30 days before we checked (7 Oct 2026), and 208 people have liked it there.

The card lists 158 languages: ab, af, ak, am, ar, as, av, ay, az, ba, bm, be and 146 more (ISO codes as given on the card).

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.

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.

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.

• canary-1b-v2 (1.0B parameters, about 2.1 GB at 4-bit before context; commercial use allowed)
• Qwen3-ASR-0.6B (0.9B parameters, about 2.0 GB at 4-bit before context; commercial use allowed)
• parakeet-ctc-1.1b (1.1B parameters, about 2.1 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.