# DeepSeek-V4-Flash-0731 GPU requirements

DeepSeek-V4-Flash-0731 has 304B parameters. To serve it, plan for about 730 GB of GPU memory in 16-bit, 365 GB in 8-bit or 183 GB in 4-bit, including about 20% for the KV cache and activations.

It is a mixture of experts: 256 experts, 6 of them active for each token. All of them stay in GPU memory, so plan memory for all 304B parameters.

[Deploy it on Arrakis](/console/#/models?model=deepseek-ai/DeepSeek-V4-Flash-0731).

## What it takes to serve it

| Precision | Memory and the smallest setup |
|---|---|
| 16-bit | 730 GB: 4 × [B300](/gpus/b300.html.md), from $18.40 per hour for all 4 |
| 8-bit | 365 GB: 2 × [B300](/gpus/b300.html.md), from $9.20 per hour for all 2 |
| 4-bit | 183 GB: one [B300](/gpus/b300.html.md), from $4.60 per GPU-hour |

## What it takes to fine-tune it

| Method | Memory and the smallest setup |
|---|---|
| QLoRA | 213 GB: one [B300](/gpus/b300.html.md), from $4.60 per GPU-hour |
| LoRA | 730 GB: 4 × [B300](/gpus/b300.html.md), from $18.40 per hour for all 4 |
| Full fine-tuning | 4,867 GB: more than one 8-GPU machine |

## About the model

| | |
|---|---|
| Parameters | `304B` |
| Experts | `256` |
| Experts for each token | `6` |
| Context window (tokens) | `1,048,576` |
| Published in | `FP8` |
| License | `mit` |
| Released | `2026-07-31` |
| Weights | [deepseek-ai/DeepSeek-V4-Flash-0731](https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731) |

## Serve it yourself

```
vllm serve deepseek-ai/DeepSeek-V4-Flash-0731 --tensor-parallel-size 4
```

## Questions

**How much GPU memory does DeepSeek-V4-Flash-0731 need?** To serve it, about 730 GB in 16-bit, 365 GB in 8-bit, 183 GB in 4-bit, including about 20% for the KV cache and activations. To fine-tune it, about 213 GB with QLoRA, 730 GB with LoRA and 4,867 GB for full fine-tuning with Adam, before activations.

**Can I run DeepSeek-V4-Flash-0731 on one GPU?** Yes, quantized. In 4-bit it needs about 183 GB, which fits on one B300. In 16-bit it needs 4 B300 GPUs.

**What does it cost to run DeepSeek-V4-Flash-0731?** In 16-bit it needs 4 B300 GPUs; in 4-bit, one B300. Each setup on this page shows the lowest price per GPU-hour on Arrakis right now, and you pay by the hour from a prepaid balance.

**How do I deploy DeepSeek-V4-Flash-0731 on Arrakis?** Open Models in the Arrakis console, paste deepseek-ai/DeepSeek-V4-Flash-0731, choose vLLM, SGLang or llama.cpp, and rent a GPU it fits on. You get an OpenAI-compatible endpoint with its own API key, and root SSH to the machine.


More models: [/models](/models.html.md).