Llama Primus Base needs about 10.1 GB of memory at its main file (a 8.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Llama Primus Base is a 8.03B-parameter Llama model in GGUF format, quantized by krgl. Its trained context length is 128K tokens. The repository has 1 quant file, from 8.5 GB to 8.5 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 8.5 GB | 10.1 GB | Too big | Get file → |
What GPU do you need for Llama Primus Base?
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: the best quant that fits is the main file (8.5 GB file, about 10.1 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Llama Primus Base
How much VRAM does Llama Primus Base need?
About 10.1 GB at its main file with an 8K context window. That is the 8.5 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 Primus Base on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Llama Primus Base GGUF?
It depends on the quant: file is 8.5 GB.
What context length does Llama Primus Base support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download Llama Primus Base GGUF?
The files are on Hugging Face in the krgl/Llama-Primus-Base_8bit-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 Primus Base use?
Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.