codegeex4-all-9b The memory it needs, what you may do with it, and the hardware it suits.
Short answer. codegeex4-all-9b needs about 12 GB of memory at 4-bit, 17 GB at 8-bit and 26 GB at full 16-bit precision, including runtime overhead and an 8,192-token KV cache. It has about 9.4 billion parameters. 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 8-bit, ANVE Office Pro (GPU) fits at 8-bit. These are estimates from its published size, not benchmarks.
01
What it is
codegeex4-all-9b is a language model for chat, drafting and question answering, published by Z.ai (Zhipu) on Hugging Face on 5 July 2024. It has about 9.4 billion parameters.
Its card lists the licence as a custom licence (codegeex4). In short, the licence sets its own terms; read it before any commercial use.
Hugging Face counted about 13,177 downloads of it in the 30 days before we checked (7 Oct 2026), and 276 people have liked it there.
The card lists 2 languages: zh, en (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 0.66 MB of KV cache at 16-bit, so 32,768 tokens would add about 21 GB.
Precision
Weights
KV cache (8,192 tokens)
Total, estimated
BF16 (full precision)
19 GB
5.4 GB
26 GB
8-bit (Q8_0)
10.0 GB
5.4 GB
17 GB
4-bit (Q4_K)
5.3 GB
5.4 GB
12 GB
03
Architecture at a glance
Setting
Value in config.json
Architecture class
ChatGLMModel
Model type
chatglm
Layers
40
Hidden size
4,096
Attention heads
32
Head size
128
Vocabulary
151,552
Stored precision
bfloat16
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 model
Verdict
ANVE One
about 48 GB of 64 GB unified memory
fits at BF16
ANVE Office
24 GB on the RTX PRO 4000 Blackwell SFF Edition
fits at 8-bit
ANVE Office Pro (GPU)
24 GB on the RTX PRO 4000 Blackwell
fits at 8-bit
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
gemma-2-9b-it (9.2B parameters, about 6.7 GB at 4-bit before context; commercial use allowed, with conditions)
gemma-2-9b (9.2B parameters, about 6.7 GB at 4-bit before context; commercial use allowed, with conditions)
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 codegeex4-all-9b need?
About 12 GB at 4-bit, 17 GB at 8-bit and 26 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 codegeex4-all-9b run on a 24 GB graphics card?
Yes, at 8-bit by this estimate, with room left for context.
Is codegeex4-all-9b free for commercial use?
Its card lists a custom licence (codegeex4), 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.
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.
