# Llama 3.1 405B GPU requirements: VRAM, GPUs and servers

> Llama 3.1 405B needs about 810 GB of VRAM in BF16, 405 GB in FP8 and 203 GB in 4-bit, plus KV cache. GPUs and servers that run it, with prices.

Source: https://overgpu.com/models/llama-3-1-405b  
Updated: 2026-11-03  
Publisher: OverGPU (https://overgpu.com/)

**In short:** Not on one GPU: in FP8 it needs about 480 GB, so it runs on an 8-GPU server such as the 8× NVIDIA HGX H100 ($16,900 a month at OverGPU).

## Model facts

- **Developer:** Meta
- **License:** Llama 3.1 Community License
- **Type:** Dense
- **Parameters:** 405B
- **Layers:** 126
- **Attention:** 128 query heads, 8 KV heads, head dimension 128
- **Context window:** 128k tokens

## How much VRAM Llama 3.1 405B needs

Weights take parameters × bytes per parameter; serving adds the KV cache and about 10% runtime overhead. Totals assume an 8k context with 8 concurrent requests and a BF16 KV cache.

| Precision | Weights | Total to serve | Cheapest OverGPU server that fits |
| --- | --- | --- | --- |
| BF16 | 810 GB | 926 GB | 8× AMD Instinct MI355X ($19,900/month) |
| FP8 | 405 GB | 480 GB | 8× NVIDIA RTX PRO 6000 Blackwell ($10,490/month) |
| 4-bit | 203 GB | 258 GB | 8× NVIDIA RTX PRO 6000 Blackwell ($10,490/month) |

## Which GPUs can run Llama 3.1 405B?

Yes = 8 concurrent requests with an 8k context each; 1 request = a single 8k request at a time; No = does not fit.

| Configuration | BF16 | FP8 | 4-bit |
| --- | --- | --- | --- |
| NVIDIA GeForce RTX 5090 (32 GB, $449/month) | No | No | No |
| NVIDIA L40S (48 GB, $890/month) | No | No | No |
| NVIDIA H100 SXM (80 GB, $2,190/month) | No | No | No |
| NVIDIA RTX PRO 6000 Blackwell (96 GB, $1,390/month) | No | No | No |
| NVIDIA H200 (141 GB, $3,090/month) | No | No | No |
| NVIDIA B200 (180 GB, $4,590/month) | No | No | No |
| NVIDIA B300 (288 GB, $5,190/month) | No | No | 1 request |
| 8× NVIDIA HGX H100 (8 × 80 GB, $16,900/month) | No | Yes | Yes |
| 8× NVIDIA RTX PRO 6000 Blackwell (8 × 96 GB, $10,490/month) | No | Yes | Yes |
| 8× NVIDIA HGX H200 (8 × 141 GB, $23,900/month) | Yes | Yes | Yes |
| 8× NVIDIA HGX B200 (8 × 180 GB, $34,900/month) | Yes | Yes | Yes |
| 8× NVIDIA HGX B300 (8 × 288 GB, $39,900/month) | Yes | Yes | Yes |
| 8× AMD Instinct MI355X (8 × 288 GB, $19,900/month) | Yes | Yes | Yes |

## Llama 3.1 405B KV cache by context length

About 516 MB per 1,000 tokens in flight with a BF16 cache.

| Context per request | 1 request | 8 requests | 32 requests |
| --- | --- | --- | --- |
| 4k tokens | 2.1 GB | 17 GB | 68 GB |
| 32k tokens | 17 GB | 135 GB | 541 GB |
| 128k tokens | 68 GB | 541 GB | 2,165 GB |

## Memory to fine-tune Llama 3.1 405B

| Method | Approximate memory | Cheapest OverGPU server that fits |
| --- | --- | --- |
| QLoRA (4-bit base) | 306 GB | 8× NVIDIA RTX PRO 6000 Blackwell ($10,490/month) |
| LoRA (BF16 base) | 1,004 GB | 8× AMD Instinct MI355X ($19,900/month) |
| Full fine-tune (AdamW, mixed precision) | 7,776 GB | More than 8 GPUs (GB300 NVL72) |

## About Llama 3.1 405B

Llama 3.1 405B is Meta’s largest dense open model: 126 layers, 8 KV heads and a 128k-token context window. At about 405 GB in FP8 it needs a full 8-GPU server, and its 126 layers make the KV cache per token the largest of the models on this site.

Every figure comes from the model's published architecture and the formulas of the VRAM calculator (https://overgpu.com/tools/vram-calculator).

## Frequently asked questions

### How much VRAM does Llama 3.1 405B need?

About 810 GB for the weights in BF16, 405 GB in FP8 and 203 GB in 4-bit, plus the KV cache: about 516 MB per 1,000 tokens in flight with a BF16 cache. Serving it in FP8 with an 8k context and 8 concurrent requests takes about 480 GB in total.

### Can Llama 3.1 405B run on a single GPU?

Not at an 8k context with 8 concurrent requests: in FP8 it needs about 480 GB, more than any single GPU holds. An 8-GPU server such as the 8× NVIDIA RTX PRO 6000 Blackwell runs it with tensor parallelism.

### What is the cheapest OverGPU server for Llama 3.1 405B?

For FP8 serving with an 8k context and 8 concurrent requests, the 8× NVIDIA RTX PRO 6000 Blackwell at $10,490 per month is the lowest-priced configuration that fits. For other contexts and concurrency, size it in the VRAM calculator.

### How much memory do I need to fine-tune Llama 3.1 405B?

Roughly 306 GB with QLoRA, 1,004 GB with LoRA on BF16 weights, and 7,776 GB for a full fine-tune with AdamW in mixed precision, before tuning batch size and sequence length. Full fine-tunes of large models are sharded across GPUs with FSDP or ZeRO-3.

## Related pages

- [LLM VRAM calculator: will your model fit on a GPU?](https://overgpu.com/tools/vram-calculator): Pick Llama, Qwen, Mistral or gpt-oss, set the precision and context length, and see weights, KV cache and which GPUs fit.
- [How much VRAM do I need for an LLM?](https://overgpu.com/blog/vram-for-llms): Quick answers for 7B, 14B, 32B, 70B and 405B models at BF16, FP8 and 4-bit, plus KV cache by context and the GPU that fits.
- [Best GPU for LLM inference in 2026: a sizing guide by model size](https://overgpu.com/blog/best-gpu-for-llm-inference): Use our 2026 sizing table, from RTX 5090 to 8× B300, to choose.
- [LLM GPU requirements](https://overgpu.com/models): VRAM, KV cache and the cheapest servers for Llama, Qwen3, Mistral and gpt-oss models.