EEVE-Korean-10.8B-instruct-v4-sft needs about 8.6 GB of memory at Q4_K_M (a 6.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 14 quants, from 4.0 GB (Q2_K) to 11.5 GB (Q8_0).
EEVE Korean 10.8B Instruct, fine‑tuned for Korean instruction following
EEVE-Korean-10.8B-instruct-v4-sft is a 10.8B parameter llama architecture model fine‑tuned for Korean instruction following. It supports a 4096 token context window and is released under the Apache‑2.0 license. The model is available in multiple GGUF quantizations.
Good at
- Korean instruction following
- Text generation with 4096 token context
- LLM inference via llama.cpp
Limits
- No vision support
- Requires 8k context for memory estimates
- License is Apache‑2.0
Best for
- Korean chatbots
- Korean content generation
- Local inference on GPUs
Who it’s for. Developers building Korean language applications who need a local, open‑source LLM. Researchers wanting to experiment with Korean instruction fine‑tuning. Teams requiring a model that can run on consumer GPUs with quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 4.0 GB | 5.4 GB | Fits | Get file → | |
| IQ3_XS | 4.5 GB | 5.8 GB | Fits | Get file → | |
| Q3_K_S | 4.7 GB | 6.0 GB | Fits | Get file → | |
| IQ3_S | 4.7 GB | 6.0 GB | Fits | Get file → | |
| IQ3_M | 4.9 GB | 6.2 GB | Fits | Get file → | |
| Q3_K_M | 5.2 GB | 6.5 GB | Fits | Get file → | |
| Q3_K_L | 5.7 GB | 7.0 GB | Fits | Get file → | |
| IQ4_XS | 5.9 GB | 7.2 GB | Fits | Get file → | |
| Q4_K_S | 6.2 GB | 7.5 GB | Tight | Get file → | |
| Q4_K_M | 6.5 GB | 7.8 GB | Tight | Get file → | |
| Q5_K_S | 7.5 GB | 8.8 GB | Too big | Get file → | |
| Q5_K_M | 7.7 GB | 9.0 GB | Too big | Get file → | |
| Q6_K | 8.9 GB | 10.2 GB | Too big | Get file → | |
| Q8_0 | 11.5 GB | 12.8 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_S (6.17 GB file, ~8.3 GB RAM). For 12 GB VRAM, Q5_K_M (7.65 GB file, ~9.8 GB RAM) or Q6_K (8.87 GB file, ~11 GB RAM). Higher‑quality quants like Q8_0 need 13.6 GB RAM and 11.48 GB file.
What GPU do you need for EEVE-Korean-10.8B-instruct-v4-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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: the best quant that fits is IQ4_XS (5.9 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (8.9 GB file, about 11.0 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (11.5 GB file, about 13.6 GB in use).
Which EEVE-Korean-10.8B-instruct-v4-sft quant should you choose?
Q4_K_M is the usual starting point for EEVE-Korean-10.8B-instruct-v4-sft: it balances file size and quality well. Here it is a 6.5 GB file.
The Q8_0 file is 11.5 GB, about 1.8 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 4.0 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
Frequently asked questions about EEVE-Korean-10.8B-instruct-v4-sft
How much VRAM does EEVE-Korean-10.8B-instruct-v4-sft need?
About 8.6 GB at Q4_K_M with an 8K context window. That is the 6.5 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 EEVE-Korean-10.8B-instruct-v4-sft on an 8 GB GPU?
Yes, with IQ4_XS: the 5.9 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of EEVE-Korean-10.8B-instruct-v4-sft GGUF?
It depends on the quant: Q2_K is 4.0 GB, IQ3_XS is 4.5 GB, Q3_K_S is 4.7 GB, IQ3_S is 4.7 GB, IQ3_M is 4.9 GB, Q3_K_M is 5.2 GB and 8 more.
What context length does EEVE-Korean-10.8B-instruct-v4-sft support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.6 GB at 8K and 0.8 GB at 4K.
Where can I download EEVE-Korean-10.8B-instruct-v4-sft GGUF?
The files are on Hugging Face in the mradermacher/EEVE-Korean-10.8B-instruct-v4-sft-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 EEVE-Korean-10.8B-instruct-v4-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 this model on 8 GB VRAM?
Yes, using the Q4_K_S quantization which requires about 8.3 GB RAM at 8k context.
Does the model support vision tasks?
No, the model has no vision capabilities.
What license applies to this model?
The model is released under the Apache‑2.0 license.