Llama-3-Open-Ko-8B-Instruct-preview 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 14 quants, from 3.2 GB (Q2_K) to 8.5 GB (Q8_0).
Llama‑3‑Open‑Ko‑8B Instruct preview in GGUF format
Llama‑3‑Open‑Ko‑8B Instruct preview is an 8.03 billion‑parameter model released by LiteLLMs. It supports Korean and English text generation and is available in multiple quantized GGUF variants. The model is licensed under "other" and is not a mixture of experts.
Good at
- Korean and English text generation
- Instruct‑style prompts
- LLM inference with llama.cpp
Limits
- No vision support
- License is other, not open source
- Context length limited to 8192 tokens
Best for
- Local inference on modest GPUs
- Fine‑tuning with llama.cpp
- Embedding generation for Korean text
Who it’s for. Developers and researchers who need a Korean‑capable Llama‑3 model for local deployment. The model is suitable for those who prefer GGUF format and have access to llama.cpp or compatible frameworks.
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 → |
For 8 GB VRAM, Q4_K_M (6.5 GB memory at 8k context) or Q5_K_M (7.3 GB) are suitable. For 12 GB VRAM, Q4_0 (6.2 GB) or Q4_K_S (6.3 GB) work well. Larger VRAM allows Q6_K (8.2 GB) or Q8_0 (10.1 GB).
What GPU do you need for Llama-3-Open-Ko-8B-Instruct-preview?
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).
Which Llama-3-Open-Ko-8B-Instruct-preview quant should you choose?
Q4_K_M is the usual starting point for Llama-3-Open-Ko-8B-Instruct-preview: 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
Frequently asked questions about Llama-3-Open-Ko-8B-Instruct-preview
How much VRAM does Llama-3-Open-Ko-8B-Instruct-preview 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 Llama-3-Open-Ko-8B-Instruct-preview 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 Llama-3-Open-Ko-8B-Instruct-preview 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 8 more.
What context length does Llama-3-Open-Ko-8B-Instruct-preview support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.
Where can I download Llama-3-Open-Ko-8B-Instruct-preview GGUF?
The files are on Hugging Face in the LiteLLMs/Llama-3-Open-Ko-8B-Instruct-preview-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 Llama-3-Open-Ko-8B-Instruct-preview use?
Hugging Face lists the license as other. 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, use Q4_K_M or Q5_K_M quantizations, which require about 6.5–7.3 GB of VRAM at 8k context.
Does this model support Korean language?
Yes, the model is trained for Korean and English, as indicated by the language tags.
Is the model open source?
The license is listed as "other"; it is not explicitly open source and may have restrictions.