multilingual-e5-large
How much memory it needs, what its licence allows, and whether it fits an office box.

multilingual-e5-large is an embedding model that turns text into vectors for document search, published by Microsoft researchers (intfloat) on Hugging Face on 30 June 2023. It has about 560 million parameters and a configured context window of 514 tokens.

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 7,160,371 downloads of it in the 30 days before we checked (7 Oct 2026), and 1,261 people have liked it there.

The card lists 94 languages: multilingual, af, am, ar, as, az, be, bg, bn, br, bs, ca and 82 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.

Inputs are short, so working memory is small next to the weights.

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.

For an office, embeddings are what make "find the clause about late fees" work across thousands of documents. The model is small, so it runs beside the main language model without crowding it.

• multilingual-e5-large-instruct: the instruction-tuned version for chat (same parameter count, so the memory figures above apply).

• Qwen3-Embedding-0.6B (0.6B parameters, about 1.8 GB at 4-bit before context; commercial use allowed)
• embeddinggemma-300m (0.3B parameters, about 1.7 GB at 4-bit before context; commercial use allowed, with conditions)
• Qwen3-VL-Embedding-2B (2.1B parameters, about 2.7 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.