CO

Codegeex4 All 9b

CodegeexGGUF by duyntnetUpdated 2024-07-27
Download on Hugging Face
Parameters9.4B
Context128K
Layers40
Architecturechatglm
Smallest quant3.1 GB
Quick answer

Codegeex4 All 9b needs about 7.1 GB of memory at Q4_K_M (a 6.3 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 27 quants, from 3.1 GB (IQ1_S) to 10.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 1.3 GB.

Codegeex4 All 9b – a 9.4B chatglm model for code generation

Codegeex4 All 9b is a 9.4 billion parameter chatglm model optimized for code generation tasks. It supports a 131072 token context window and is available in multiple GGUF quantizations. The model can be run with llama.cpp, JanAI, KoboldCPP, text-generation-webui, ollama, and GPT4All.

Good at

  • Code completion and infilling
  • Multi‑language code generation
  • Prompt‑based code explanations

Limits

  • No vision support
  • Requires large VRAM for higher quantizations
  • License type is other

Best for

  • Developers needing fast code suggestions
  • Educational tools for coding tutorials
  • Automated code review assistants

Who it’s for. Engineers and researchers who need a lightweight code generation model that can run locally. The model is suitable for developers who prefer open‑source inference clients and can manage the required VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S3.1 GB 3.9 GB
Fits Get file →
IQ1_M3.2 GB 4.1 GB
Fits Get file →
IQ2_XXS3.4 GB 4.3 GB
Fits Get file →
IQ2_XS3.6 GB 4.4 GB
Fits Get file →
IQ2_S3.8 GB 4.6 GB
Fits Get file →
IQ2_M3.9 GB 4.8 GB
Fits Get file →
Q2_K_S4.0 GB 4.8 GB
Fits Get file →
Q2_K4.0 GB 4.8 GB
Fits Get file →
IQ3_XXS4.3 GB 5.1 GB
Fits Get file →
IQ3_XS4.4 GB 5.3 GB
Fits Get file →
IQ3_S4.6 GB 5.4 GB
Fits Get file →
Q3_K_S4.6 GB 5.4 GB
Fits Get file →
IQ3_M4.8 GB 5.6 GB
Fits Get file →
Q3_K_M5.1 GB 5.9 GB
Fits Get file →
IQ4_XS5.3 GB 6.1 GB
Fits Get file →
Q3_K_L5.3 GB 6.1 GB
Fits Get file →
IQ4_NL5.5 GB 6.3 GB
Fits Get file →
Q4_05.5 GB 6.3 GB
Fits Get file →
Q4_K_S5.8 GB 6.6 GB
Fits Get file →
Q4_16.0 GB 6.8 GB
Fits Get file →
Q4_K_M6.3 GB 7.1 GB
Fits Get file →
Q5_06.6 GB 7.4 GB
Tight Get file →
Q5_K_S6.7 GB 7.5 GB
Tight Get file →
Q5_17.1 GB 7.9 GB
Tight Get file →
Q5_K_M7.1 GB 8.0 GB
Tight Get file →
Q6_K8.3 GB 9.1 GB
Too big Get file →
Q8_010.0 GB 10.8 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (3.1 GB) or IQ1_M (3.22 GB). If you have 12 GB VRAM, Q4_K_M (6.25 GB) or Q5_K_M (7.14 GB) are suitable. Higher quantizations such as Q8_0 (9.99 GB) need 16 GB or more VRAM. Memory estimates are approximate.

What GPU do you need for Codegeex4 All 9b?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is IQ1_S (3.1 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q3_K_M (5.1 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (7.1 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (10.0 GB file, about 10.8 GB in use).

Which Codegeex4 All 9b quant should you choose?

Q4_K_M is the usual starting point for Codegeex4 All 9b: it balances file size and quality well. Here it is a 6.3 GB file.

The Q8_0 file is 10.0 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is IQ1_S at 3.1 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturechatglm
Parameters9.4B
Layers40
Trained context131,072 tokens
KV cache (fp16)40 KB per token

Source

Quantized byduyntnet
FamilyCodegeex
Licenseother
Downloads (HF)938
Last updated2024-07-27

Frequently asked questions about Codegeex4 All 9b

How much VRAM does Codegeex4 All 9b need?

About 7.1 GB at Q4_K_M with an 8K context window. That is the 6.3 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Codegeex4 All 9b on an 8 GB GPU?

Yes, with Q5_K_M: the 7.1 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Codegeex4 All 9b GGUF?

It depends on the quant: IQ1_S is 3.1 GB, IQ1_M is 3.2 GB, IQ2_XXS is 3.4 GB, IQ2_XS is 3.6 GB, IQ2_S is 3.8 GB, IQ2_M is 3.9 GB and 21 more.

What context length does Codegeex4 All 9b support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.3 GB at 32K.

Where can I download Codegeex4 All 9b GGUF?

The files are on Hugging Face in the duyntnet/codegeex4-all-9b-imatrix-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Codegeex4 All 9b use?

Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Codegeex4 All 9b on 8 GB VRAM?

Yes, use the IQ1_S or IQ1_M quantization which requires about 3.9–4.1 GB of VRAM at 8k context.

Does this model support image inputs?

No, Codegeex4 All 9b does not have vision capabilities.

Which inference client is recommended for quick setup?

llama.cpp and text-generation-webui are popular choices for fast local deployment.

Similar models

Browse all →

More from duyntnet

All by duyntnet →

More Codegeex models

All Codegeex →

Other small models

All small models →