ANVE: the private AI office, on the record. See what that means

ANVE

Run it on your own hardware · updated 2026-10-16

Nemotron-Nano-9B-v2
Memory at each precision, the licence in plain words, and where it fits.

Short answer. Nemotron-Nano-9B-v2 needs about 8.4 GB of memory at 4-bit, 13 GB at 8-bit and 21 GB at full 16-bit precision, including runtime overhead and an 8,192-token KV cache. It has about 8.9 billion parameters and a 131,072-token context window. 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.

01

What it is

Nemotron-Nano-9B-v2 is a language model for chat, drafting and question answering, published by NVIDIA on Hugging Face on 12 August 2025. It has about 8.9 billion parameters and a configured context window of 131,072 tokens.

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 331,709 downloads of it in the 30 days before we checked (7 Oct 2026), and 524 people have liked it there.

The card lists 6 languages: en, es, fr, de, it, ja (ISO codes as given on the card).

It is built on nvidia/NVIDIA-Nemotron-Nano-12B-v2-Base, according to its card.

02

How much memory it needs

How these figures are worked out: weights = parameters × bits per weight ÷ 8. The KV cache is added for 8,192 tokens of context, plus about 1.5 GB of runtime overhead. Treat the totals as planning estimates.

Each token of context adds about 0.23 MB of KV cache at 16-bit, so 32,768 tokens would add about 7.5 GB.

PrecisionWeightsKV cache (8,192 tokens)Total, estimated
BF16 (full precision)18 GB1.9 GB21 GB
8-bit (Q8_0)9.4 GB1.9 GB13 GB
4-bit (Q4_K)5.0 GB1.9 GB8.4 GB
03

Architecture at a glance

SettingValue in config.json
Architecture classNemotronHForCausalLM
Model typenemotron_h
Layers56
Hidden size4,480
Attention heads40
Key-value heads8 (grouped-query attention)
Head size128
Vocabulary131,072
Configured context131,072
Stored precisionbfloat16
04

Will it fit on ANVE?

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.

Configuration (at launch)Memory for the modelVerdict
ANVE Oneabout 48 GB of 64 GB unified memoryfits at BF16
ANVE Office24 GB on the RTX PRO 4000 Blackwell SFF Editionfits at BF16
ANVE Office Pro (GPU)24 GB on the RTX PRO 4000 Blackwellfits at BF16
05

What an office would use it for

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.

06

Similar models to compare

  • internlm3-8b-instruct (8.8B parameters, about 6.5 GB at 4-bit before context; commercial use allowed)
  • granite-4.2-8b (8.8B parameters, about 6.4 GB at 4-bit before context; commercial use allowed)
  • EuroLLM-9B-Instruct-2512 (9.2B parameters, about 6.6 GB at 4-bit before context; commercial use allowed)
07

Questions people ask

How much memory does Nemotron-Nano-9B-v2 need?
About 8.4 GB at 4-bit, 13 GB at 8-bit and 21 GB at full 16-bit precision, including an 8,192-token KV cache and about 1.5 GB of runtime overhead. These are estimates from its parameter count.
Can Nemotron-Nano-9B-v2 run on a 24 GB graphics card?
Yes, at BF16 by this estimate, with room left for context.
Is Nemotron-Nano-9B-v2 free for commercial use?
Its card lists a custom licence (nvidia-open-model-license), which sets its own terms; read it before any commercial use. Read the licence itself before relying on this summary; it is not legal advice.
What is Nemotron-Nano-9B-v2’s context window?
Its configuration sets 131,072 tokens. Longer contexts need more memory for the KV cache, so the practical limit on a given machine can be lower.
08

What is not real yet

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.