KO

Kordef 12b

KordefGGUF by mradermacherUpdated 2026-11-01
Download on Hugging Face
Parameters11.8B
Context128K
Layers48
Architecturegemma3
Smallest quant4.8 GB
Quick answer

Kordef 12b needs about 11.0 GB of memory at Q4_K_M (a 7.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 11 quants, from 4.8 GB (Q2_K) to 12.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.

Kordef 12b – 12B‑parameter Gemma‑3 model fine‑tuned on Korean defense documents

Kordef 12b is a 12B‑parameter Gemma‑3 model fine‑tuned on Korean defense administrative‑rule and educational PDFs. It is released for research and educational use only. The model is available in multiple GGUF quantizations.

Good at

  • Domain‑specific Korean defense QA
  • Instruction‑tuned Korean language tasks
  • Research on Korean professional‑domain LLMs

Limits

  • No vision support
  • Not for safety‑critical military use
  • License restricts autonomous decision‑making

Best for

  • Academic research on Korean NLP
  • Educational reference‑style QA
  • Reproducibility studies in Korean defense domain

Who it’s for. Researchers and educators working on Korean language modeling and domain adaptation. The model is suitable for academic projects that require a Korean defense‑domain foundation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.8 GB 8.5 GB
Too big Get file →
Q3_K_S5.5 GB 9.2 GB
Too big Get file →
Q3_K_M6.0 GB 9.7 GB
Too big Get file →
Q3_K_L6.5 GB 10.2 GB
Too big Get file →
IQ4_XS6.6 GB 10.3 GB
Too big Get file →
Q4_K_S6.9 GB 10.7 GB
Too big Get file →
Q4_K_M7.3 GB 11.0 GB
Too big Get file →
Q5_K_S8.2 GB 12.0 GB
Too big Get file →
Q5_K_M8.4 GB 12.2 GB
Too big Get file →
Q6_K9.7 GB 13.4 GB
Too big Get file →
Q8_012.5 GB 16.2 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (file size 6.94 GB, estimated 10.7 GB memory). For 12 GB VRAM, Q5_K_M (8.45 GB, 12.2 GB memory) is a good balance. For 16 GB VRAM, Q8_0 (12.51 GB, 16.2 GB memory) provides the highest quality.

What GPU do you need for Kordef 12b?

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: the best quant that fits is Q5_K_S (8.2 GB file, about 12.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (9.7 GB file, about 13.4 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (12.5 GB file, about 16.2 GB in use).

Which Kordef 12b quant should you choose?

Q4_K_M is the usual starting point for Kordef 12b: it balances file size and quality well. Here it is a 7.3 GB file.

The Q8_0 file is 12.5 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 4.8 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

Architecturegemma3
Parameters11.8B
Layers48
Trained context131,072 tokens
KV cache (fp16)384 KB per token

Source

Quantized bymradermacher
FamilyKordef
Licensegemma
Downloads (HF)620
Last updated2026-11-01

Frequently asked questions about Kordef 12b

How much VRAM does Kordef 12b need?

About 11.0 GB at Q4_K_M with an 8K context window. That is the 7.3 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 Kordef 12b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Kordef 12b GGUF?

It depends on the quant: Q2_K is 4.8 GB, Q3_K_S is 5.5 GB, Q3_K_M is 6.0 GB, Q3_K_L is 6.5 GB, IQ4_XS is 6.6 GB, Q4_K_S is 6.9 GB and 5 more.

What context length does Kordef 12b support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.2 GB at 8K and 12.9 GB at 32K.

Where can I download Kordef 12b GGUF?

The files are on Hugging Face in the mradermacher/kordef-12b-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 Kordef 12b use?

Hugging Face lists the license as gemma. 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 Kordef 12b on 8 GB VRAM?

Use the Q4_K_S quant, which requires about 10.7 GB of memory at 8 k context. It will fit on 8 GB VRAM with some swapping.

Is Kordef 12b suitable for production deployment?

The model is released for research and educational use only and is not intended for autonomous decision‑making or safety‑critical applications.

What languages does Kordef 12b support?

The model is trained on Korean defense documents and is primarily designed for Korean language tasks.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

Other medium models

All medium models →