KORMo 10B Sft needs about 8.4 GB of memory at Q4_K_M (a 6.6 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 0.0 GB to 8.8 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
KORMo 10B Sft – 10.8B parameter Korean/English LLM
KORMo 10B Sft is a 10.8B parameter fully open LLM trained on Korean and English data. It supports reasoning and tool usage. The model is released under Apache 2.0 and is fully reproducible.
Good at
- Reasoning tasks
- Tool integration
- Bilingual Korean/English
Limits
- No vision support
- Not safety‑tuned
- Large context requires high VRAM
Best for
- Chatbot development
- Code generation
- Data analysis
Who it’s for. Developers building Korean/English applications who need a large, open‑source LLM. Researchers wanting to reproduce or extend the model.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.8 GB | Fits | Get file → | |
| IQ1_S | 2.6 GB | 4.4 GB | Fits | Get file → | |
| IQ1_M | 2.8 GB | 4.6 GB | Fits | Get file → | |
| IQ2_XXS | 3.1 GB | 5.0 GB | Fits | Get file → | |
| IQ2_XS | 3.4 GB | 5.2 GB | Fits | Get file → | |
| IQ2_S | 3.6 GB | 5.4 GB | Fits | Get file → | |
| IQ2_M | 3.8 GB | 5.7 GB | Fits | Get file → | |
| Q2_K_S | 3.9 GB | 5.7 GB | Fits | Get file → | |
| Q2_K | 4.2 GB | 6.0 GB | Fits | Get file → | |
| IQ3_XXS | 4.3 GB | 6.2 GB | Fits | Get file → | |
| IQ3_XS | 4.6 GB | 6.5 GB | Fits | Get file → | |
| Q3_K_S | 4.8 GB | 6.7 GB | Fits | Get file → | |
| IQ3_S | 4.9 GB | 6.7 GB | Fits | Get file → | |
| IQ3_M | 5.0 GB | 6.8 GB | Fits | Get file → | |
| Q3_K_M | 5.3 GB | 7.2 GB | Fits | Get file → | |
| Q3_K_L | 5.7 GB | 7.6 GB | Tight | Get file → | |
| IQ4_XS | 5.9 GB | 7.7 GB | Tight | Get file → | |
| IQ4_NL | 6.2 GB | 8.1 GB | Too big | Get file → | |
| Q4_0 | 6.2 GB | 8.1 GB | Too big | Get file → | |
| Q4_K_S | 6.2 GB | 8.1 GB | Too big | Get file → | |
| Q4_K_M | 6.6 GB | 8.4 GB | Too big | Get file → | |
| Q4_1 | 6.8 GB | 8.7 GB | Too big | Get file → | |
| Q5_K_S | 7.5 GB | 9.3 GB | Too big | Get file → | |
| Q5_K_M | 7.7 GB | 9.5 GB | Too big | Get file → | |
| Q6_K | 8.8 GB | 10.7 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (est. 8.4 GB at 8 k context). For 12 GB VRAM, Q5_K_M (est. 9.5 GB). For 16 GB VRAM, Q6_K (est. 10.7 GB). Smaller quants such as IQ1_S or IQ1_M require less VRAM but are larger on disk.
What GPU do you need for KORMo 10B Sft?
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 the main file (0.0 GB file, about 1.8 GB in use).
- 6 GB VRAM: the best quant that fits is Q2_K (4.2 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is IQ4_XS (5.9 GB file, about 7.7 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (8.8 GB file, about 10.7 GB in use).
Which KORMo 10B Sft quant should you choose?
Q4_K_M is the usual starting point for KORMo 10B Sft: it balances file size and quality well. Here it is a 6.6 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about KORMo 10B Sft
How much VRAM does KORMo 10B Sft need?
About 8.4 GB at Q4_K_M with an 8K context window. That is the 6.6 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 KORMo 10B Sft on an 8 GB GPU?
Yes, with IQ4_XS: the 5.9 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of KORMo 10B Sft GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 2.6 GB, IQ1_M is 2.8 GB, IQ2_XXS is 3.1 GB, IQ2_XS is 3.4 GB, IQ2_S is 3.6 GB and 19 more.
What context length does KORMo 10B Sft support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.
Where can I download KORMo 10B Sft GGUF?
The files are on Hugging Face in the mradermacher/KORMo-10B-sft-i1-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 KORMo 10B Sft 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 KORMo 10B Sft on 8 GB VRAM?
Yes, using the Q4_K_M quant which estimates 8.4 GB VRAM at 8 k context. It is close to the limit, so a slightly lower context may be needed.
Is the model safe for production use?
The model has not been safety‑tuned or preference‑aligned, so it may produce undesired repetitions in complex reasoning tasks.
What license applies to this model?
The model is released under Apache 2.0, allowing free use and modification.