LLaMA v2 needs about 18.3 GB of memory at F16 (a 13.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 0.0 GB to 13.5 GB.
LLaMA v2 is a 6.74B-parameter Llama model in GGUF format, quantized by YashRawal225. Its trained context length is 4K tokens. The repository has 3 quant files, from 0.0 GB to 13.5 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 2.6 GB | Fits | Get file → | |
| F16 | 13.5 GB | 16.1 GB | Too big | Get file → | |
| — | 13.5 GB | 16.1 GB | Too big | Get file → |
What GPU do you need for LLaMA v2?
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 the main file (0.0 GB file, about 4.8 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 4.8 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 4.8 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 4.8 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (13.5 GB file, about 18.3 GB in use).
Which LLaMA v2 quant should you choose?
F16 (13.5 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
If memory is tight, the smallest file is the first one in the table at 0.0 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 v2
How much VRAM does LLaMA v2 need?
About 18.3 GB at F16 with an 8K context window. That is the 13.5 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 v2 on an 8 GB GPU?
Yes, with the smaller files: the 0.0 GB file needs about 4.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of LLaMA v2 GGUF?
It depends on the quant: file is 0.0 GB, F16 is 13.5 GB, file is 13.5 GB.
What context length does LLaMA v2 support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.
Where can I download LLaMA v2 GGUF?
The files are on Hugging Face in the YashRawal225/llama-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 v2 use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.