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

ANVE

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

GLM-4.6
The memory it needs, what you may do with it, and the hardware it suits.

Short answer. GLM-4.6 needs about 205 GB of memory at 4-bit, 384 GB at 8-bit and 718 GB at full 16-bit precision, including runtime overhead and an 8,192-token KV cache. It has about 356.8 billion parameters and a 202,752-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

GLM-4.6 is a language model for chat, drafting and question answering, published by Z.ai (Zhipu) on Hugging Face on 29 September 2025. It has about 356.8 billion parameters and a configured context window of 202,752 tokens. It is a mixture-of-experts model: 160 experts, 8 used for each token.

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 17,166 downloads of it in the 30 days before we checked (7 Oct 2026), and 1,235 people have liked it there.

The card lists 2 languages: en, zh (ISO codes as given on the 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 0.38 MB of KV cache at 16-bit, so 32,768 tokens would add about 12 GB.

PrecisionWeightsKV cache (8,192 tokens)Total, estimated
BF16 (full precision)714 GB3.1 GB718 GB
8-bit (Q8_0)379 GB3.1 GB384 GB
4-bit (Q4_K)201 GB3.1 GB205 GB
03

Architecture at a glance

SettingValue in config.json
Architecture classGlm4MoeForCausalLM
Model typeglm4_moe
Layers92
Hidden size5,120
Attention heads96
Key-value heads8 (grouped-query attention)
Head size128
Vocabulary151,552
Experts160, 8 active per token
Configured context202,752
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

  • Llama-3.1-405B-Instruct (405.9B parameters, about 230 GB at 4-bit before context; commercial use allowed, with conditions)
  • MiMo-V2.5 (310.8B parameters, about 176 GB at 4-bit before context; commercial use allowed)
  • MiMo-V2-Flash (309.8B parameters, about 176 GB at 4-bit before context; commercial use allowed)
07

Questions people ask

How much memory does GLM-4.6 need?
About 205 GB at 4-bit, 384 GB at 8-bit and 718 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-4.6 run on a 24 GB graphics card?
Not entirely: even at 4-bit it needs about 205 GB, so part of it would sit in system memory, which is much slower.
Is GLM-4.6 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-4.6’s context window?
Its configuration sets 202,752 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.