How much memory does GLM-4.5V need?

About 64 GB at 4-bit, 117 GB at 8-bit and 218 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-4.5V run on a 24 GB graphics card?

Not entirely: even at 4-bit it needs about 64 GB, so part of it would sit in system memory, which is much slower.

Is GLM-4.5V 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-4.5V’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.

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

ANVE

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

GLM-4.5V
How much memory it needs, what its licence allows, and whether it fits an office box.

Short answer. GLM-4.5V needs about 64 GB of memory at 4-bit, 117 GB at 8-bit and 218 GB at full 16-bit precision, including runtime overhead and an 8,192-token KV cache. It has about 107.7 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 does not fit, ANVE Office only with partial offload to system memory, which is much slower, ANVE Office Pro (GPU) only with partial offload to system memory, which is much slower. These are estimates from its published size, not benchmarks.

What it is

GLM-4.5V 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 10 August 2025. It has about 107.7 billion parameters and a configured context window of 65,536 tokens. It is a mixture-of-experts model: 128 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 39,691 downloads of it in the 30 days before we checked (7 Oct 2026), and 722 people have liked it there.

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

It is built on zai-org/GLM-4.5-Air-Base, according to its card.

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 0.19 MB of KV cache at 16-bit, so 32,768 tokens would add about 6.2 GB.

Precision	Weights	KV cache (8,192 tokens)	Total, estimated
BF16 (full precision)	215 GB	1.5 GB	218 GB
8-bit (Q8_0)	114 GB	1.5 GB	117 GB
4-bit (Q4_K)	61 GB	1.5 GB	64 GB

Architecture at a glance

Setting	Value in config.json
Architecture class	Glm4vMoeForConditionalGeneration
Model type	glm4v_moe
Layers	46
Hidden size	4,096
Attention heads	96
Key-value heads	8 (grouped-query attention)
Head size	128
Vocabulary	151,552
Experts	128, 8 active per token
Configured context	65,536
Stored precision	bfloat16

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 model	Verdict
ANVE One	about 48 GB of 64 GB unified memory	does not fit
ANVE Office	24 GB on the RTX PRO 4000 Blackwell SFF Edition	only with partial offload to system memory, which is much slower
ANVE Office Pro (GPU)	24 GB on the RTX PRO 4000 Blackwell	only with partial offload to system memory, which is much slower

What an office would use it for

Models this large are stronger on long, hard drafting and reasoning, but need most of a 64 to 128 GB machine even at 4-bit, which leaves less room for long documents and several users.

Similar models to compare

Llama-4-Scout-17B-16E-Instruct (108.6B parameters, about 63 GB at 4-bit before context; commercial use allowed, with conditions)
Qwen3.5-122B-A10B (125.1B parameters, about 72 GB at 4-bit before context; commercial use allowed)
Qwen3.8-Flash-Next (180.0B parameters, about 103 GB at 4-bit before context; custom licence: check before commercial use)

Questions people ask

How much memory does GLM-4.5V need?: About 64 GB at 4-bit, 117 GB at 8-bit and 218 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-4.5V run on a 24 GB graphics card?: Not entirely: even at 4-bit it needs about 64 GB, so part of it would sit in system memory, which is much slower.
Is GLM-4.5V 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-4.5V’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.

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.

GLM-4.5VHow much memory it needs, what its licence allows, and whether it fits an office box.