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

ANVE

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

GLM-4.1V-9B-Thinking
Memory at each precision, the licence in plain words, and where it fits.

Short answer. GLM-4.1V-9B-Thinking needs about 7.6 GB of memory at 4-bit, 13 GB at 8-bit and 22 GB at full 16-bit precision, including runtime overhead and an 8,192-token KV cache. It has about 10.3 billion parameters and a 65,536-token context window. Licence in short: commercial use allowed. 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

GLM-4.1V-9B-Thinking is a vision-language model: it reads images (scanned pages, photos, charts and screenshots) as well as text, published by Z.ai (Zhipu) on Hugging Face on 28 June 2025. It has about 10.3 billion parameters and a configured context window of 65,536 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 167,009 downloads of it in the 30 days before we checked (7 Oct 2026), and 791 people have liked it there.

The card lists 2 languages: en, zh (ISO codes as given on the card).

It is built on zai-org/GLM-4-9B-0414, according to its card.

02

How much memory it needs

We size it the way you would size any model: the weights (parameters × bits ÷ 8), the KV cache for 8,192 tokens of context, and roughly 1.5 GB for the runtime itself. Real use varies with settings.

Each token of context adds about 0.04 MB of KV cache at 16-bit, so 32,768 tokens would add about 1.3 GB.

PrecisionWeightsKV cache (8,192 tokens)Total, estimated
BF16 (full precision)21 GB0.34 GB22 GB
8-bit (Q8_0)11 GB0.34 GB13 GB
4-bit (Q4_K)5.8 GB0.34 GB7.6 GB
03

Architecture at a glance

SettingValue in config.json
Architecture classGlm4vForConditionalGeneration
Model typeglm4v
Layers40
Hidden size4,096
Attention heads32
Key-value heads2 (grouped-query attention)
Head size128
Vocabulary151,552
Configured context65,536
Stored precisionbfloat16
04

Will it fit on ANVE?

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.

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

  • Llama-3.2-11B-Vision-Instruct (10.7B parameters, about 7.5 GB at 4-bit before context; commercial use allowed, with conditions)
  • Apertus-v1.5-8B (8.9B parameters, about 6.5 GB at 4-bit before context; commercial use allowed)
  • Qwen3-VL-8B-Instruct (8.8B parameters, about 6.4 GB at 4-bit before context; commercial use allowed)
07

Questions people ask

How much memory does GLM-4.1V-9B-Thinking need?
About 7.6 GB at 4-bit, 13 GB at 8-bit and 22 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 GLM-4.1V-9B-Thinking run on a 24 GB graphics card?
Yes, at BF16 by this estimate, with room left for context.
Is GLM-4.1V-9B-Thinking free for commercial use?
Its card lists MIT, which allows commercial use, modification and redistribution as long as the copyright notice is kept. Read the licence itself before relying on this summary; it is not legal advice.
What is GLM-4.1V-9B-Thinking’s context window?
Its configuration sets 65,536 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.