JEJUMA 002 needs about 6.5 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 15 quants, from 3.2 GB (Q2_K) to 16.1 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
8B Llama model for Korean dialect translation
JEJUMA 002 is an 8.03B parameter Llama model fine‑tuned for Korean dialect translation and detection. It supports translation between Jeju dialect and standard Korean, and can detect dialects. The model is released under the MIT license.
Good at
- Dialect to standard Korean translation
- Standard to dialect translation
- Dialect detection
Limits
- No vision support
- Limited to Korean dialects
- Requires 131072 token context
Best for
- Translating Jeju dialect to standard Korean
- Converting standard Korean to Jeju dialect
- Detecting Korean dialects in text
Who it’s for. Developers building Korean language tools, researchers studying regional dialects, and users needing accurate dialect translation. The model is suitable for applications that require precise translation between Jeju dialect and standard Korean.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 3.2 GB | 4.8 GB | Fits | Get file → | |
| Q3_K_S | 3.7 GB | 5.2 GB | Fits | Get file → | |
| Q3_K_M | 4.0 GB | 5.6 GB | Fits | Get file → | |
| Q3_K_L | 4.3 GB | 5.9 GB | Fits | Get file → | |
| Q4_0 | 4.7 GB | 6.2 GB | Fits | Get file → | |
| Q4_K_S | 4.7 GB | 6.3 GB | Fits | Get file → | |
| Q4_K_M | 4.9 GB | 6.5 GB | Fits | Get file → | |
| Q4_1 | 5.1 GB | 6.7 GB | Fits | Get file → | |
| Q5_0 | 5.6 GB | 7.2 GB | Fits | Get file → | |
| Q5_K_S | 5.6 GB | 7.2 GB | Fits | Get file → | |
| Q5_K_M | 5.7 GB | 7.3 GB | Tight | Get file → | |
| Q5_1 | 6.1 GB | 7.6 GB | Tight | Get file → | |
| Q6_K | 6.6 GB | 8.2 GB | Too big | Get file → | |
| Q8_0 | 8.5 GB | 10.1 GB | Too big | Get file → | |
| — | 16.1 GB | 17.6 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 4.92 GB, estimated 6.5 GB memory). For 12 GB VRAM, Q5_K_M (5.73 GB, 7.3 GB memory) is a good balance. If more VRAM is available, Q6_K (6.6 GB, 8.2 GB memory) offers higher quality.
What GPU do you need for JEJUMA 002?
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 Q3_K_L (4.3 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_1 (6.1 GB file, about 7.6 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (16.1 GB file, about 17.6 GB in use).
Which JEJUMA 002 quant should you choose?
Q4_K_M is the usual starting point for JEJUMA 002: it balances file size and quality well. Here it is a 4.9 GB file.
The Q8_0 file is 8.5 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 3.2 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 JEJUMA 002
How much VRAM does JEJUMA 002 need?
About 6.5 GB at Q4_K_M with an 8K context window. That is the 4.9 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 JEJUMA 002 on an 8 GB GPU?
Yes, with Q5_1: the 6.1 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of JEJUMA 002 GGUF?
It depends on the quant: Q2_K is 3.2 GB, Q3_K_S is 3.7 GB, Q3_K_M is 4.0 GB, Q3_K_L is 4.3 GB, Q4_0 is 4.7 GB, Q4_K_S is 4.7 GB and 9 more.
What context length does JEJUMA 002 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download JEJUMA 002 GGUF?
The files are on Hugging Face in the joongi007/JEJUMA-002-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 JEJUMA 002 use?
Hugging Face lists the license as mit. 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 JEJUMA 002 on 8 GB VRAM?
Yes, the Q4_K_M quantization requires about 6.5 GB memory at 8 k context, which fits within 8 GB VRAM.
Does the model support other dialects besides Jeju?
The model is trained on Jeju dialect and standard Korean; it can detect dialects but translation is focused on Jeju.
Is the model chat‑ready?
No, the model is designed for translation tasks only and does not support conversational prompting.