Xevn 4B needs about 4.4 GB of memory at Q4_K_M (a 2.8 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 5 quants, from 2.8 GB (Q4_K_M) to 8.7 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.4 GB.
Xevn 4B – a 4B Korean decision model for quick choice answering
Xevn 4B is a 4B decision model built for Korean understanding and judgment. It follows the Jev decision format, reading a question and its options once and returning an answer with probability. No text generation; each request costs one forward pass.
Good at
- Korean decision tasks
- Fast single-pass inference
- Probability‑based answer selection
Limits
- No text generation
- Requires 8k context for memory estimates
- Apache‑2.0 license
Best for
- Korean QA systems
- Decision support tools
- Rapid prototyping of choice models
Who it’s for. Developers building Korean language decision systems or tools that need quick, probabilistic answers without generating text. The model is suitable for lightweight inference environments where memory is limited.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 2.8 GB | 4.4 GB | Fits | Get file → | |
| Q5_K_M | 3.2 GB | 4.8 GB | Fits | Get file → | |
| Q6_K | 3.6 GB | 5.2 GB | Fits | Get file → | |
| Q8_0 | 4.6 GB | 6.2 GB | Fits | Get file → | |
| BF16 | 8.7 GB | 10.3 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 2.78 GB, estimated 4.4 GB memory at 8k context). If more VRAM is available, Q5_K_M (3.16 GB, 4.8 GB memory) or Q6_K (3.56 GB, 5.2 GB memory) provide higher precision. The BF16 file (8.67 GB, 10.3 GB memory) requires more than 10 GB VRAM.
What GPU do you need for Xevn 4B?
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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is Q6_K (3.6 GB file, about 5.2 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.6 GB file, about 6.2 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (8.7 GB file, about 10.3 GB in use).
Which Xevn 4B quant should you choose?
Q4_K_M is the usual starting point for Xevn 4B: it balances file size and quality well. Here it is a 2.8 GB file.
The Q8_0 file is 4.6 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Xevn 4B
How much VRAM does Xevn 4B need?
About 4.4 GB at Q4_K_M with an 8K context window. That is the 2.8 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 Xevn 4B on an 8 GB GPU?
Yes, with Q8_0: the 4.6 GB file needs about 6.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Xevn 4B GGUF?
It depends on the quant: Q4_K_M is 2.8 GB, Q5_K_M is 3.2 GB, Q6_K is 3.6 GB, Q8_0 is 4.6 GB, BF16 is 8.7 GB.
What context length does Xevn 4B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.4 GB at 32K.
Where can I download Xevn 4B GGUF?
The files are on Hugging Face in the quevirus/Xevn-4B-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 Xevn 4B 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 Xevn 4B on 8 GB VRAM?
Yes, the Q4_K_M quantized file requires about 4.4 GB memory at 8k context, fitting within 8 GB VRAM.
Does Xevn 4B support English?
Yes, the model supports Korean primarily and English as a secondary language.
Is there a text generation mode?
No, Xevn 4B is a decision model and does not generate text.