A.X 4.0 Light needs about 5.4 GB of memory at Q4_K_M (a 4.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 16 quants, from 2.8 GB (Q2_K) to 29.0 GB (F32).
7.26B parameter Qwen2 based Korean LLM
A.X 4.0 Light is a 7.26B parameter model built on Qwen2.5 and trained on Korean data. It supports up to 16,384 tokens context and is licensed under apache-2.0. The model is optimized for reasoning and tool use.
Good at
- Korean language tasks
- Reasoning with tools
- Long context up to 16,384 tokens
Limits
- No vision support
- Requires at least 3.8 GB VRAM for Q2_K
- License is apache-2.0
Best for
- Chatbots in Korean
- Enterprise Korean NLP
- Tool‑enabled workflows
Who it’s for. Developers building Korean‑centric applications who need a lightweight yet capable LLM. The model is suitable for on‑premise deployment where GPU memory is limited.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 2.8 GB | 3.8 GB | Fits | Get file → | |
| Q3_K_S | 3.3 GB | 4.2 GB | Fits | Get file → | |
| Q3_K_M | 3.6 GB | 4.6 GB | Fits | Get file → | |
| Q3_K_L | 3.9 GB | 4.8 GB | Fits | Get file → | |
| IQ4_XS | 4.0 GB | 5.0 GB | Fits | Get file → | |
| Q4_0 | 4.2 GB | 5.2 GB | Fits | Get file → | |
| Q4_K_S | 4.2 GB | 5.2 GB | Fits | Get file → | |
| IQ4_NL | 4.2 GB | 5.2 GB | Fits | Get file → | |
| Q4_K_M | 4.4 GB | 5.4 GB | Fits | Get file → | |
| Q5_0 | 5.0 GB | 6.0 GB | Fits | Get file → | |
| Q5_K_S | 5.0 GB | 6.0 GB | Fits | Get file → | |
| Q5_K_M | 5.2 GB | 6.1 GB | Fits | Get file → | |
| Q6_K | 6.0 GB | 6.9 GB | Fits | Get file → | |
| Q8_0 | 7.7 GB | 8.7 GB | Too big | Get file → | |
| BF16 | 14.5 GB | 15.5 GB | Too big | Get file → | |
| F32 | 29.0 GB | 30.0 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K (file size 2.81 GB, memory 3.8 GB) or Q3_K_S (3.27 GB, 4.2 GB). If 12 GB VRAM is available, Q4_K_M (4.44 GB, 5.4 GB) offers better quality. For 16 GB VRAM, Q5_K_M (5.18 GB, 6.1 GB) balances size and performance.
What GPU do you need for A.X 4.0 Light?
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 Q2_K (2.8 GB file, about 3.8 GB in use).
- 6 GB VRAM: the best quant that fits is Q5_0 (5.0 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q6_K (6.0 GB file, about 6.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (7.7 GB file, about 8.7 GB in use).
- 16 GB VRAM: the best quant that fits is BF16 (14.5 GB file, about 15.5 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (14.5 GB file, about 15.5 GB in use).
- 32 GB VRAM: the best quant that fits is F32 (29.0 GB file, about 30.0 GB in use).
Which A.X 4.0 Light quant should you choose?
Q4_K_M is the usual starting point for A.X 4.0 Light: it balances file size and quality well. Here it is a 4.4 GB file.
The Q8_0 file is 7.7 GB, about 1.7 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 Q2_K at 2.8 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 A.X 4.0 Light
How much VRAM does A.X 4.0 Light need?
About 5.4 GB at Q4_K_M with an 8K context window. That is the 4.4 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 A.X 4.0 Light on an 8 GB GPU?
Yes, with Q6_K: the 6.0 GB file needs about 6.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of A.X 4.0 Light GGUF?
It depends on the quant: Q2_K is 2.8 GB, Q3_K_S is 3.3 GB, Q3_K_M is 3.6 GB, Q3_K_L is 3.9 GB, IQ4_XS is 4.0 GB, Q4_0 is 4.2 GB and 10 more.
What context length does A.X 4.0 Light support?
The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 0.5 GB at 8K and 0.9 GB at 16K.
Where can I download A.X 4.0 Light GGUF?
The files are on Hugging Face in the mykor/A.X-4.0-Light-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 A.X 4.0 Light use?
Hugging Face lists the license as apache-2.0. 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 A.X 4.0 Light on 8 GB VRAM?
Yes, the Q2_K quant requires 3.8 GB VRAM, which fits within an 8 GB GPU. Other quants need more memory.
Does the model support vision tasks?
No, the model does not include vision capabilities.
What is the maximum context length?
The lightweight version supports up to 16,384 tokens context length.