LL

Llama 3.2 Korean Bllossom 3B

LlamaGGUF by BllossomUpdated 2024-12-13
Download on Hugging Face
Parameters3.21B
Context128K
Layers28
Architecturellama
Smallest quant2.0 GB
Quick answer

Llama 3.2 Korean Bllossom 3B needs about 3.5 GB of memory at Q4_K_M (a 2.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

Llama 3.2 Korean Bllossom 3B – 3.21B parameter Korean language model

Llama 3.2 Korean Bllossom 3B is a 3.21B parameter model trained on 131072 context tokens. It supports tools and is available in a single Q4_K_M quantized GGUF file. The model is released under the llama3.2 license.

Good at

  • Tool usage
  • Korean language understanding
  • Contextual reasoning

Limits

  • No vision support
  • Requires 3.5 GB VRAM at 8 k context
  • License is llama3.2

Best for

  • Chatbots in Korean
  • Korean content generation
  • Tool‑enabled assistants

Who it’s for. Developers building Korean language applications who need a compact, tool‑aware model. Researchers interested in Korean Llama 3.2 variants may also use it.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.0 GB 3.5 GB
Fits Get file →

The only available quant is Q4_K_M with a file size of 2.02 GB. It requires approximately 3.5 GB VRAM at 8 k context. For 8 GB VRAM setups, this quant is suitable. No other quants are provided.

What GPU do you need for Llama 3.2 Korean Bllossom 3B?

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 Q4_K_M (2.0 GB file, about 3.5 GB in use).

Which Llama 3.2 Korean Bllossom 3B quant should you choose?

Q4_K_M is the usual starting point for Llama 3.2 Korean Bllossom 3B: it balances file size and quality well. Here it is a 2.0 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters3.21B
Layers28
Trained context131,072 tokens
KV cache (fp16)112 KB per token

Source

Quantized byBllossom
FamilyLlama
Licensellama3.2
Downloads (HF)370
Last updated2024-12-13

Frequently asked questions about Llama 3.2 Korean Bllossom 3B

How much VRAM does Llama 3.2 Korean Bllossom 3B need?

About 3.5 GB at Q4_K_M with an 8K context window. That is the 2.0 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 3.2 Korean Bllossom 3B on an 8 GB GPU?

Yes, with Q4_K_M: the 2.0 GB file needs about 3.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Llama 3.2 Korean Bllossom 3B GGUF?

It depends on the quant: Q4_K_M is 2.0 GB.

What context length does Llama 3.2 Korean Bllossom 3B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.

Where can I download Llama 3.2 Korean Bllossom 3B GGUF?

The files are on Hugging Face in the Bllossom/llama-3.2-Korean-Bllossom-3B-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 3.2 Korean Bllossom 3B use?

Hugging Face lists the license as llama3.2. 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 quant requires about 3.5 GB VRAM at 8 k context, well within an 8 GB budget.

Does this model support vision?

No, the model does not include vision capabilities.

What license applies to this model?

The model is released under the llama3.2 license.

Similar models

Browse all →

More from Bllossom

All by Bllossom →

More Llama models

All Llama →

Other tiny models

All tiny models →