OLMoE-1B-7B-0125-Instruct
Memory at each precision, the licence in plain words, and where it fits.

OLMoE-1B-7B-0125-Instruct is a language model for chat, drafting and question answering, published by the Allen Institute for AI (Ai2) on Hugging Face on 27 January 2025. It has about 6.9 billion parameters and a configured context window of 4,096 tokens. It is a mixture-of-experts model: 64 experts, 8 used for each token.

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 142,081 downloads of it in the 30 days before we checked (7 Oct 2026), and 68 people have liked it there.

It is built on allenai/OLMoE-1B-7B-0125-DPO, according to its card.

The arithmetic: parameters × bits per weight ÷ 8 gives the weights; add the KV cache, which grows with every token of context; then add about 1.5 GB for the runtime. These are estimates for planning, not measurements.

Each token of context adds about 0.13 MB of KV cache at 16-bit, so 32,768 tokens would add about 4.3 GB.

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.

This size suits quick drafting, classification, extraction and chat over short documents on modest hardware. ANVE pairs a fast 4B-class model with its main model for quick jobs.

• OLMoE-1B-7B-0924-Instruct: a later dated release of the same model (same parameter count, so the memory figures above apply).

• deepseek-coder-7b-instruct-v1.5 (6.9B parameters, about 5.4 GB at 4-bit before context; custom licence: check before commercial use)
• granite-4.0-h-tiny (6.9B parameters, about 5.4 GB at 4-bit before context; commercial use allowed)
• Llama-2-7b-chat-hf (6.7B parameters, about 5.3 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.