LL

Llama-3-Open-Ko-8B

LlamaGGUF by teddylee777Updated 2024-05-20
Download on Hugging Face
Parameters8B
Context8K
Layers32
Architecturellama
Smallest quant4.7 GB
Quick answer

Llama-3-Open-Ko-8B 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 10 quants, from 4.7 GB (Q4_0) to 16.1 GB.

Llama‑3‑Open‑Ko‑8B – 8B‑parameter Korean‑focused LLM

Llama‑3‑Open‑Ko‑8B is an 8B‑parameter language model based on the Llama‑3 architecture. It was trained on over 60GB of deduplicated public text and processes more than 17.7B tokens. The model supports 8k context length and is available in several GGUF quantizations.

Good at

  • Large‑context Korean text generation
  • Code generation
  • Instruction‑style dialogue

Limits

  • No vision support
  • License: llama3
  • No fine‑tuned instruction set

Best for

  • Chatbot prototypes
  • Text summarization
  • Code assistance

Who it’s for. Researchers and developers needing a Korean‑centric LLM for text and code tasks. The model is suitable for commercial and academic projects that require a large‑context, transformer‑based language model.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_04.7 GB 6.2 GB
Fits Get file →
Q4_K_S4.7 GB 6.3 GB
Fits Get file →
Q4_K_M4.9 GB 6.5 GB
Fits Get file →
Q4_15.1 GB 6.7 GB
Fits Get file →
Q5_05.6 GB 7.2 GB
Fits Get file →
Q5_K_S5.6 GB 7.2 GB
Fits Get file →
Q5_K_M5.7 GB 7.3 GB
Tight Get file →
Q6_K6.6 GB 8.2 GB
Too big Get file →
Q8_08.5 GB 10.1 GB
Too big Get file →
—16.1 GB 17.6 GB
Too big Get file →

For 8GB VRAM, Q4_0 (4.66 GB, 6.2 GB memory) or Q4_K_S (4.69 GB, 6.3 GB memory) are suitable. With 12GB VRAM, Q4_K_M (4.92 GB, 6.5 GB memory) or Q5_0 (5.6 GB, 7.2 GB memory) fit comfortably. For 16GB VRAM, Q6_K (6.6 GB, 8.2 GB memory) or Q8_0 (8.54 GB, 10.1 GB memory) are recommended.

What GPU do you need for Llama-3-Open-Ko-8B?

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 Q5_K_M (5.7 GB file, about 7.3 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (16.1 GB file, about 17.6 GB in use).

Which Llama-3-Open-Ko-8B quant should you choose?

Q4_K_M is the usual starting point for Llama-3-Open-Ko-8B: 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 Q4_0 at 4.7 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized byteddylee777
FamilyLlama
Licensellama3
Downloads (HF)1,558
Last updated2024-05-20

Frequently asked questions about Llama-3-Open-Ko-8B

How much VRAM does Llama-3-Open-Ko-8B 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 on an 8 GB GPU?

Yes, with Q5_K_M: the 5.7 GB file needs about 7.3 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 GGUF?

It depends on the quant: Q4_0 is 4.7 GB, Q4_K_S is 4.7 GB, Q4_K_M is 4.9 GB, Q4_1 is 5.1 GB, Q5_0 is 5.6 GB, Q5_K_S is 5.6 GB and 4 more.

What context length does Llama-3-Open-Ko-8B 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 GGUF?

The files are on Hugging Face in the teddylee777/Llama-3-Open-Ko-8B-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 use?

Hugging Face lists the license as llama3. 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 Llama‑3‑Open‑Ko‑8B on 8 GB VRAM?

Yes, use Q4_0 or Q4_K_S quantizations. They require about 6.2–6.3 GB memory at 8k context.

Does this model support Korean instruction fine‑tuning?

The base model is not fine‑tuned with Korean instruction sets. It can be further trained for instruction tasks.

What context length does the model support?

The model supports a maximum context length of 8192 tokens.

Similar models

Browse all →

More from teddylee777

All by teddylee777 →

More Llama models

All Llama →

Other small models

All small models →