Meta Llama 3.1 405B Instruct needs about 89.5 GB of memory at Q2_K (a 79.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 3 quants, from 71.8 GB (Q2_K) to 231.2 GB (Q4_0).
Meta Llama 3.1 405B Instruct is a 210B-parameter Llama model in GGUF format, quantized by leafspark. The repository has 3 quant files, from 71.8 GB (Q2_K) to 231.2 GB (Q4_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 71.8 GB (4 parts) | 80.9 GB | Too big | Get file → | |
| Q2_K | 79.4 GB (4 parts) | 89.5 GB | Too big | Get file → | |
| Q4_0 | 231.2 GB (12 parts) | 259.5 GB | Too big | Get file → |
What GPU do you need for Meta Llama 3.1 405B Instruct?
These figures add the file size, an fp16 KV cache at an 8K context window 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: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: no quant fits at an 8K context.
Which Meta Llama 3.1 405B Instruct quant should you choose?
Q2_K (79.4 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
If memory is tight, the smallest file is Q2_K at 71.8 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about Meta Llama 3.1 405B Instruct
How much VRAM does Meta Llama 3.1 405B Instruct need?
About 89.5 GB at Q2_K with an 8K context window. That is the 79.4 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 Meta Llama 3.1 405B Instruct on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 80.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Meta Llama 3.1 405B Instruct GGUF?
It depends on the quant: Q2_K is 71.8 GB, Q2_K is 79.4 GB, Q4_0 is 231.2 GB.
Where can I download Meta Llama 3.1 405B Instruct GGUF?
The files are on Hugging Face in the leafspark/Meta-Llama-3.1-405B-Instruct-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 Meta Llama 3.1 405B Instruct 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.