Llama 3 Kor BCCard needs about 22.9 GB of memory at its main file (a 20.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 5 quants, from 12.4 GB to 39.0 GB.
Llama 3 Kor BCCard is a 11.7B-parameter Llama model in GGUF format, quantized by sh2orc. Its trained context length is 8K tokens. The repository has 5 quant files, from 12.4 GB to 39.0 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 12.4 GB | 14.5 GB | Too big | Get file → | |
| — | 16.3 GB | 18.5 GB | Too big | Get file → | |
| — | 20.7 GB | 22.9 GB | Too big | Get file → | |
| — | 23.3 GB | 25.4 GB | Too big | Get file → | |
| — | 39.0 GB | 41.1 GB | Too big | Get file → |
What GPU do you need for Llama 3 Kor BCCard?
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: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is the main file (12.4 GB file, about 14.5 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (20.7 GB file, about 22.9 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (23.3 GB file, about 25.4 GB in use).
- 48 GB VRAM: the best quant that fits is the main file (39.0 GB file, about 41.1 GB in use).
Which Llama 3 Kor BCCard quant should you choose?
If memory is tight, the smallest file is the first one in the table at 12.4 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Llama 3 Kor BCCard
How much VRAM does Llama 3 Kor BCCard need?
About 22.9 GB at its main file with an 8K context window. That is the 20.7 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 Kor BCCard on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 14.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Llama 3 Kor BCCard GGUF?
It depends on the quant: file is 12.4 GB, file is 16.3 GB, file is 20.7 GB, file is 23.3 GB, file is 39.0 GB.
What context length does Llama 3 Kor BCCard support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.6 GB at 8K and 1.6 GB at 8K.
Where can I download Llama 3 Kor BCCard GGUF?
The files are on Hugging Face in the sh2orc/Llama-3-Kor-BCCard-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 Kor BCCard 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.