What GPU do I need to run meta-llama/Llama-3.1-405B?
405.9B parameters, published in BF16. View on Hugging FaceGated
Set up Llama-3.1-405BLlama-3.1-405B is published by meta-llama on Hugging Face, with 141,703 downloads and 987 likes to date. It's a LlamaForCausalLM model built for text-generation, published natively in BF16, and gated: you'll need to accept the model's terms on Hugging Face before downloading weights.
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision, plus a fixed overhead for KV-cache, activations, and fragmentation. Full formula and assumptions: methodology.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 756.0 GB | 907.2 GB | No capable live offer found | – | – |
| FP8 (quantized) | 378.0 GB | 453.6 GB | RTX PRO 6000 | 5 | $6.88/hr |
| INT4 (quantized) | 189.0 GB | 226.8 GB | RTX A6000 | 5 | $1.81/hr |
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Llama-3.1-405B: common questions
Can Llama-3.1-405B run on a single GPU?
Not on a desktop card. At BF16 it needs 907.2 GB of VRAM, more than a single 32 GB desktop card holds. No card currently listed on the marketplace both supports BF16 and has enough VRAM for it, so how many it would take is not something this page can answer today.
Do I need approval to download Llama-3.1-405B?
Yes. meta-llama gates this repository on Hugging Face, so you have to accept its terms with a signed-in account before the weights will download. It does not change the 907.2 GB the model needs once you have them.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More Llama 3.1 models
- Llama-3.1-405B-Instruct (405.9B, BF16)
- Llama-3.1-405B-FP8 (405.9B, F8_E4M3)
- Llama-3.3-70B-Instruct-FP8-dynamic (70.6B, F8_E4M3)
- Meta-Llama-3.1-70B-Instruct-FP8 (70.6B, F8_E4M3)
- Llama-3.1-70B-Instruct (70.6B, BF16)
Related reading: H100 pricing and specs, The best GPUs for AI, ranked, and Best GPU for LLM inference.
