LL

llama-3-Korean-Bllossom-8B

LlamaGGUF by MLP-KTLimUpdated 2024-07-03
Download on Hugging Face
Parameters8.03B
Context8K
Layers32
Architecturellama
Smallest quant4.9 GB
Quick answer

llama-3-Korean-Bllossom-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.

Korean‑English bilingual LLM based on Llama3 with 8.03B parameters

llama-3-Korean-Bllossom-8B is an 8.03‑billion‑parameter model trained on 250 GB of Korean data. It supports Korean and English instruction following and is fine‑tuned with human feedback. The model is available in GGUF format for efficient inference.

Good at

  • Korean‑English bilingual generation
  • Instruction following with Korean cultural context
  • Human‑feedback tuned responses

Limits

  • Context length 8192 tokens
  • Approx. 6.5 GB VRAM needed for Q4_K_M
  • No vision support in GGUF

Best for

  • Korean language generation
  • Bilingual translation tasks
  • Cultural content creation

Who it’s for. Developers and researchers who need a Korean‑English LLM for text generation or translation. The model runs on CPU and can be accelerated with 8 GB GPU using the Q4_K_M quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M4.9 GB 6.5 GB
Fits Get file →

The Q4_K_M quantized file is 4.92 GB and requires about 6.5 GB VRAM at 8 k context. It is suitable for systems with 8 GB or more GPU memory. For lower memory budgets, a higher‑quantization model would be needed, but such files are not provided here.

What GPU do you need for llama-3-Korean-Bllossom-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 Q4_K_M (4.9 GB file, about 6.5 GB in use).

Which llama-3-Korean-Bllossom-8B quant should you choose?

Q4_K_M is the usual starting point for llama-3-Korean-Bllossom-8B: it balances file size and quality well. Here it is a 4.9 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8.03B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized byMLP-KTLim
FamilyLlama
Licensellama3
Downloads (HF)790
Last updated2024-07-03

Frequently asked questions about llama-3-Korean-Bllossom-8B

How much VRAM does llama-3-Korean-Bllossom-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-Korean-Bllossom-8B on an 8 GB GPU?

Yes, with Q4_K_M: the 4.9 GB file needs about 6.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of llama-3-Korean-Bllossom-8B GGUF?

It depends on the quant: Q4_K_M is 4.9 GB.

What context length does llama-3-Korean-Bllossom-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-Korean-Bllossom-8B GGUF?

The files are on Hugging Face in the MLP-KTLim/llama-3-Korean-Bllossom-8B-gguf-Q4_K_M 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-Korean-Bllossom-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 this model on 8 GB VRAM?

Yes, the Q4_K_M quantized model requires approximately 6.5 GB VRAM, which fits within an 8 GB GPU.

Does this model support vision tasks?

No, the GGUF version does not include vision support.

What is the maximum context length?

The model supports up to 8192 tokens of context.

Other GGUFs of llama-3-Korean-Bllossom-8B

Similar models

Browse all →

More Llama models

All Llama →

Other small models

All small models →