What GPU do I need to run meta-llama/Llama-3.1-405B-FP8?
405.9B parameters, published in F8_E4M3. View on Hugging FaceGated
Llama-3.1-405B-FP8 is published by meta-llama on Hugging Face, with 488,296 downloads and 124 likes to date. It's a LlamaForCausalLM model built for text-generation, published natively in F8_E4M3, 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 times a flat 1.2 overhead for activations and fragmentation. The KV-cache grows with context and is not in that factor; it is listed per model below where the architecture is published. Full formula and assumptions: methodology.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| FP8 (native) | 378.0 GB | 453.6 GB | RTX PRO 6000 | 5 | $6.88/hr |
| INT4 (quantized) | 189.0 GB | 226.8 GB | RTX A6000 | 5 | $1.82/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.
Cheapest way to run Llama-3.1-405B-FP8 at its published (F8_E4M3) precision: 5× RTX PRO 6000, at $1.38/hr per GPU ($6.88/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
Llama-3.1-405B-FP8: KV cache by context length
The KV cache is the memory the attention layers hold for every token of context, on top of the weights. It is not part of the flat 1.2x overhead in the table above, grows with context length and with every concurrent request, and is why a long-context deployment needs more VRAM than the table shows.
KV-cache size for Llama-3.1-405B-FP8 is not published for this architecture, so no figure is shown.
Llama-3.1-405B-FP8: common questions
Can Llama-3.1-405B-FP8 run on a single GPU?
No. At FP8 (native) it needs 453.6 GB of VRAM, more than a single 32 GB desktop card holds. The cheapest capable card in the live feed is a 95.0 GB RTX PRO 6000, and it takes 5 of them.
Do I need approval to download Llama-3.1-405B-FP8?
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 453.6 GB the model needs once you have them.
Is Llama-3.1-405B-FP8 already quantized?
Yes. It is published in FP8, one byte per parameter, so the 453.6 GB figure is already a quantized footprint rather than a full-precision one. Only INT4 goes below it, at 226.8 GB. A GPU without FP8 tensor cores cannot run it as published, which is why cards here are matched on precision support and not on VRAM alone.
How many GPUs do I need to run Llama-3.1-405B-FP8?
5 at FP8 (native). It needs 453.6 GB of VRAM and the cheapest capable live offer is a 95.0 GB RTX PRO 6000, so 5 of them come to $6.88/hr in total.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More Llama 3.1 models
- Llama-3.1-405B (405.9B, BF16)
- Llama-3.1-405B-Instruct (405.9B, BF16)
- 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)
Alternatives at this size
Other models for text-generation within about a third of Llama-3.1-405B-FP8's 405.9B parameters, from other model lines.
- MiMo-V2.5 (310.8B, F8_E4M3)
- NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 (560.5B, BF16)
- Ornith-1.5-397B (403.4B, BF16)
- GLM-4.5 (358.3B, BF16)
- Hy3-preview (298.8B, BF16)
More on Llama-3.1-405B-FP8
Fits on a 288 GB GPU at INT4: every model that fits in 288 GB.
Related reading: RTX PRO 6000 pricing and specs, How much VRAM you need for LLMs, Serving LLMs with vLLM, vLLM vs TensorRT-LLM vs SGLang, and Best GPU for LLM inference.
Related on Aquanode: All Nemotron VoiceChat models and their GPU requirements, Llama-3.1-70B-Instruct vs Qwen2.5-72B-Instruct: VRAM, context and license, GPU requirements for Meta-Llama-3.1-8B, GPU requirements for CodeLlama-34b-Instruct-hf, and GPU requirements for Llama-2-13b-hf.
Your own GPU cloud accounts
One console for the GPU clouds you already rent from. Your keys stay on your machine.
$20 a month, flat