Darwin 28B KR Legal needs about 19.2 GB of memory at Q4_K_M (a 16.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 10.7 GB (Q2_K) to 28.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
Darwin 28B KR Legal – Korean legal domain multimodal model
Darwin 28B KR Legal is a 26.9 billion‑parameter Qwen3.5‑based model fine‑tuned on Korean court cases, statutes, and bar exam data. It supports reasoning, tools, and vision. The model is released under Apache 2.0.
Good at
- Legal reasoning in Korean
- Multimodal document analysis
- Bar exam question answering
Limits
- No vision support on CPU only
- Requires ~55 GB VRAM for BF16 inference
- No non‑Korean language support
Best for
- Legal research and case summary
- Drafting Korean legal documents
- Studying Korean bar exam material
Who it’s for. Developers building Korean legal assistants, law firms needing automated document review, educators preparing bar exam content. The model is suitable for environments with high‑end GPUs or CPU inference via llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 10.7 GB | 13.4 GB | Too big | Get file → | |
| Q3_K_S | 12.1 GB | 14.7 GB | Too big | Get file → | |
| Q3_K_M | 13.3 GB | 15.9 GB | Too big | Get file → | |
| Q3_K_L | 14.3 GB | 17.0 GB | Too big | Get file → | |
| IQ4_XS | 15.2 GB | 17.8 GB | Too big | Get file → | |
| Q4_K_S | 15.6 GB | 18.2 GB | Too big | Get file → | |
| Q4_K_M | 16.5 GB | 19.2 GB | Too big | Get file → | |
| Q5_K_S | 18.7 GB | 21.3 GB | Too big | Get file → | |
| Q5_K_M | 19.2 GB | 21.9 GB | Too big | Get file → | |
| Q6_K | 22.1 GB | 24.7 GB | Too big | Get file → | |
| Q8_0 | 28.6 GB | 31.2 GB | Too big | Get file → |
For 8 GB VRAM use Q2_K (10.71 GB file, 13.4 GB memory at 8k context). For 16 GB VRAM use Q4_K_M (16.55 GB file, 19.2 GB memory). For 24 GB VRAM use Q6_K (22.08 GB file, 24.7 GB memory).
What GPU do you need for Darwin 28B KR Legal?
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: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is Q3_K_M (13.3 GB file, about 15.9 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_M (19.2 GB file, about 21.9 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (28.6 GB file, about 31.2 GB in use).
Which Darwin 28B KR Legal quant should you choose?
Q4_K_M is the usual starting point for Darwin 28B KR Legal: it balances file size and quality well. Here it is a 16.5 GB file.
The Q8_0 file is 28.6 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.
If memory is tight, the smallest file is Q2_K at 10.7 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 Darwin 28B KR Legal
How much VRAM does Darwin 28B KR Legal need?
About 19.2 GB at Q4_K_M with an 8K context window. That is the 16.5 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 Darwin 28B KR Legal on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 13.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Darwin 28B KR Legal GGUF?
It depends on the quant: Q2_K is 10.7 GB, Q3_K_S is 12.1 GB, Q3_K_M is 13.3 GB, Q3_K_L is 14.3 GB, IQ4_XS is 15.2 GB, Q4_K_S is 15.6 GB and 5 more.
What context length does Darwin 28B KR Legal support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.
Where can I download Darwin 28B KR Legal GGUF?
The files are on Hugging Face in the mradermacher/Darwin-28B-KR-Legal-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 Darwin 28B KR Legal 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 Darwin 28B KR Legal on 8 GB VRAM?
Use the Q2_K quant; it requires 13.4 GB memory at 8k context, so it will not fit on 8 GB VRAM.
Does the model support English text?
The model is specialized for Korean legal content and does not guarantee accurate English handling.
What license applies to this model?
The model is released under Apache 2.0, inherited from its base.