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

ANVE

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

command-a-plus-05-2026-bf16
The memory it needs, what you may do with it, and the hardware it suits.

Short answer. command-a-plus-05-2026-bf16 needs about 125 GB of memory at 4-bit, 234 GB at 8-bit and 439 GB at full 16-bit precision, including runtime overhead and an 8,192-token KV cache. It has about 218.8 billion parameters and a 200,000-token context window. Licence in short: commercial use allowed. By memory alone, on ANVE’s launch configurations: ANVE One does not fit, ANVE Office does not fit, ANVE Office Pro (GPU) does not fit. These are estimates from its published size, not benchmarks.

01

What it is

command-a-plus-05-2026-bf16 is a vision-language model: it reads images (scanned pages, photos, charts and screenshots) as well as text, published by Cohere Labs on Hugging Face on 11 May 2026. It has about 218.8 billion parameters and a configured context window of 200,000 tokens. It is a mixture-of-experts model: 128 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 34,827 downloads of it in the 30 days before we checked (7 Oct 2026), and 145 people have liked it there.

The card lists 48 languages: en, ar, bg, bn, ca, cs, da, de, el, es, et, fa and 36 more (ISO codes as given on the card).

02

How much memory it needs

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 0.03 MB of KV cache at 16-bit, so 32,768 tokens would add about 1.1 GB. 24 of its 32 layers use sliding-window attention, so the real cache is smaller than this full-attention estimate.

PrecisionWeightsKV cache (8,192 tokens)Total, estimated
BF16 (full precision)438 GB0.27 GB439 GB
8-bit (Q8_0)232 GB0.27 GB234 GB
4-bit (Q4_K)123 GB0.27 GB125 GB
03

Architecture at a glance

SettingValue in config.json
Architecture classCohere2VisionForConditionalGeneration
Model typecohere2_vision
Layers32
Hidden size4,096
Attention heads128
Key-value heads8 (grouped-query attention)
Head size128
Vocabulary262,144
Experts128, 8 active per token
Configured context200,000
Stored precisionbfloat16
04

Will it fit on ANVE?

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 modelVerdict
ANVE Oneabout 48 GB of 64 GB unified memorydoes not fit
ANVE Office24 GB on the RTX PRO 4000 Blackwell SFF Editiondoes not fit
ANVE Office Pro (GPU)24 GB on the RTX PRO 4000 Blackwelldoes not fit
05

What an office would use it for

This is frontier-scale: even at 4-bit it needs far more memory than any single office box, so it belongs on a multi-GPU server or a cloud service, not on an appliance.

06

Similar models to compare

  • Qwen3.8-Flash-Next (180.0B parameters, about 103 GB at 4-bit before context; custom licence: check before commercial use)
  • GLM-5.3-Flash (321.3B parameters, about 182 GB at 4-bit before context; commercial use allowed)
  • Qwen3.5-122B-A10B (125.1B parameters, about 72 GB at 4-bit before context; commercial use allowed)
07

Questions people ask

How much memory does command-a-plus-05-2026-bf16 need?
About 125 GB at 4-bit, 234 GB at 8-bit and 439 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 command-a-plus-05-2026-bf16 run on a 24 GB graphics card?
Not entirely: even at 4-bit it needs about 125 GB, so part of it would sit in system memory, which is much slower.
Is command-a-plus-05-2026-bf16 free for commercial use?
Its card lists Apache 2.0, which allows commercial use, modification and redistribution, with attribution and a copy of the licence, and includes a patent grant. Read the licence itself before relying on this summary; it is not legal advice.
What is command-a-plus-05-2026-bf16’s context window?
Its configuration sets 200,000 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.