Llama 3.1 Quantized 4bit needs about 6.1 GB of memory at IQ4_XS (a 4.5 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 2 quants, from 4.5 GB (IQ4_XS) to 37.9 GB (IQ4_XS). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Llama 3.1 Quantized 4bit is a 70.6B-parameter Llama model in GGUF format, quantized by PersonalAILabs. Its trained context length is 128K tokens. The repository has 2 quant files, from 4.5 GB (IQ4_XS) to 37.9 GB (IQ4_XS).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ4_XS | 4.5 GB | 6.1 GB | Fits | Get file → | |
| IQ4_XS | 37.9 GB | 39.5 GB | Too big | Get file → |
What GPU do you need for Llama 3.1 Quantized 4bit?
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: the best quant that fits is IQ4_XS (4.5 GB file, about 6.1 GB in use).
- 12 GB VRAM: the best quant that fits is IQ4_XS (4.5 GB file, about 6.1 GB in use).
- 16 GB VRAM: the best quant that fits is IQ4_XS (4.5 GB file, about 6.1 GB in use).
- 24 GB VRAM: the best quant that fits is IQ4_XS (4.5 GB file, about 6.1 GB in use).
- 32 GB VRAM: the best quant that fits is IQ4_XS (4.5 GB file, about 6.1 GB in use).
- 48 GB VRAM: the best quant that fits is IQ4_XS (37.9 GB file, about 39.5 GB in use).
Which Llama 3.1 Quantized 4bit quant should you choose?
IQ4_XS (4.5 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Llama 3.1 Quantized 4bit
How much VRAM does Llama 3.1 Quantized 4bit need?
About 6.1 GB at IQ4_XS with an 8K context window. That is the 4.5 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 3.1 Quantized 4bit on an 8 GB GPU?
Yes, with IQ4_XS: the 4.5 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Llama 3.1 Quantized 4bit GGUF?
It depends on the quant: IQ4_XS is 4.5 GB, IQ4_XS is 37.9 GB.
What context length does Llama 3.1 Quantized 4bit 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 3.1 Quantized 4bit GGUF?
The files are on Hugging Face in the PersonalAILabs/Llama-3.1-Quantized-4bit 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 3.1 Quantized 4bit use?
Hugging Face lists the license as llama3.1. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.