codegeex4-all-9b needs about 5.6 GB of memory at IQ3_M (a 4.8 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 25 quants, from 3.1 GB (IQ1_S) to 18.8 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 1.3 GB.
CodeGeeX4-ALL-9B: 9B multilingual code generation model in GGUF format
CodeGeeX4-ALL-9B is a 9‑billion‑parameter multilingual code generation model. It supports code completion, generation, interpreter, web search, function call, and repository‑level Q&A. The model is available in multiple GGUF quantizations for llama.cpp inference.
Good at
- Code completion and generation
- Multilingual code support
- Repository‑level code Q&A
Limits
- Large context size of 131072 tokens
- Requires at least 3.9 GB VRAM for IQ1_S at 8 k context
- License is other, not standard
Best for
- Developers needing code generation
- Teams building code assistants
- Researchers testing multilingual code models
Who it’s for. The model is suitable for developers and researchers who require a high‑performance code generation model in a GGUF format. It is ideal for local inference with llama.cpp and for integration into code‑centric applications.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 3.1 GB | 3.9 GB | Fits | Get file → | |
| IQ1_M | 3.2 GB | 4.1 GB | Fits | Get file → | |
| IQ2_XXS | 3.4 GB | 4.3 GB | Fits | Get file → | |
| IQ2_XS | 3.6 GB | 4.4 GB | Fits | Get file → | |
| IQ2_S | 3.8 GB | 4.6 GB | Fits | Get file → | |
| IQ2_M | 3.9 GB | 4.8 GB | Fits | Get file → | |
| Q2_K_S | 4.0 GB | 4.8 GB | Fits | Get file → | |
| Q2_K | 4.0 GB | 4.8 GB | Fits | Get file → | |
| IQ3_XXS | 4.3 GB | 5.1 GB | Fits | Get file → | |
| IQ3_XS | 4.4 GB | 5.3 GB | Fits | Get file → | |
| IQ3_S | 4.6 GB | 5.4 GB | Fits | Get file → | |
| Q3_K_S | 4.6 GB | 5.4 GB | Fits | Get file → | |
| IQ3_M | 4.8 GB | 5.6 GB | Fits | Get file → | |
| Q3_K | 5.1 GB | 5.9 GB | Fits | Get file → | |
| IQ4_XS | 5.3 GB | 6.1 GB | Fits | Get file → | |
| Q3_K_L | 5.3 GB | 6.1 GB | Fits | Get file → | |
| IQ4_NL | 5.5 GB | 6.3 GB | Fits | Get file → | |
| Q4_K_S | 5.8 GB | 6.6 GB | Fits | Get file → | |
| Q4_K | 6.3 GB | 7.1 GB | Fits | Get file → | |
| Q5_K_S | 6.7 GB | 7.5 GB | Tight | Get file → | |
| Q5_K | 7.1 GB | 8.0 GB | Tight | Get file → | |
| Q6_K | 8.3 GB | 9.1 GB | Too big | Get file → | |
| Q8_0 | 10.0 GB | 10.8 GB | Too big | Get file → | |
| BF16 | 18.8 GB | 19.6 GB | Too big | Get file → | |
| — | 18.8 GB | 19.6 GB | Too big | Get file → |
For 8 GB VRAM, use IQ4_K or Q4_K (≈6.6 GB). For 12 GB VRAM, IQ5_K or Q5_K (≈7.5–8 GB) gives better quality. If memory is limited to 4 GB, IQ1_S or IQ1_M are the only options.
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 (5.1 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K (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).
- 16 GB VRAM: the best quant that fits is Q8_0 (10.0 GB file, about 10.8 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (18.8 GB file, about 19.6 GB in use).
Which codegeex4-all-9b quant should you choose?
IQ3_M (4.8 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
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
Source
Frequently asked questions about codegeex4-all-9b
How much VRAM does codegeex4-all-9b need?
About 5.6 GB at IQ3_M with an 8K context window. That is the 4.8 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: 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 19 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 legraphista/codegeex4-all-9b-IMat-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 IQ4_K or Q4_K quantizations which require about 6.6 GB VRAM at 8 k context.
Does the model support vision tasks?
No, the model is purely for code generation and does not include vision capabilities.
What is the maximum context length?
The model was trained on 131072 tokens and supports that full context length.