Llama3 8B 1.58 100B tokens needs about 4.0 GB of memory at its main file (a 2.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 2.5 GB to 2.5 GB.
Llama3 8B 1.58 100B tokens is a 8.03B-parameter Llama model in GGUF format, quantized by nebuxcloud. The repository has 2 quant files, from 2.5 GB to 2.5 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 2.5 GB | 4.0 GB | Fits | Get file → | |
| — | 2.5 GB | 4.0 GB | Fits | Get file → |
What GPU do you need for Llama3 8B 1.58 100B tokens?
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 the main file (2.5 GB file, about 4.0 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Llama3 8B 1.58 100B tokens
How much VRAM does Llama3 8B 1.58 100B tokens need?
About 4.0 GB at its main file with an 8K context window. That is the 2.5 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 Llama3 8B 1.58 100B tokens on an 8 GB GPU?
Yes, with the smaller files: the 2.5 GB file needs about 4.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Llama3 8B 1.58 100B tokens GGUF?
It depends on the quant: file is 2.5 GB, file is 2.5 GB.
Where can I download Llama3 8B 1.58 100B tokens GGUF?
The files are on Hugging Face in the nebuxcloud/Llama3-8B-1.58-100B-tokens-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.