llama 3.2 3B Elite needs about 4.9 GB of memory at its main file (a 3.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
llama 3.2 3B Elite is a 3.21B-parameter Llama model in GGUF format, quantized by Jackrong. Its trained context length is 128K tokens. The repository has 1 quant file, from 3.4 GB to 3.4 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 3.4 GB | 4.9 GB | Fits | Get file → |
What GPU do you need for llama 3.2 3B Elite?
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 (3.4 GB file, about 4.9 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about llama 3.2 3B Elite
How much VRAM does llama 3.2 3B Elite need?
About 4.9 GB at its main file with an 8K context window. That is the 3.4 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 3B Elite on an 8 GB GPU?
Yes, with the smaller files: the 3.4 GB file needs about 4.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of llama 3.2 3B Elite GGUF?
It depends on the quant: file is 3.4 GB.
What context length does llama 3.2 3B Elite 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 3B Elite GGUF?
The files are on Hugging Face in the Jackrong/llama-3.2-3B-Elite 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 3B Elite 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.