# DeepSeek-V4-Flash by DeepSeek: GPU Requirements and Cost
Source: https://savrn.com/models/deepseek-v4-flash/gpus
Markdown alternate of the page above; the site index is https://savrn.com/llms.txt

---

## Every Accelerator, Every Precision

How many cards of each accelerator the SAVRN Index prices it takes to hold DeepSeek-V4-Flash, and what that many cards cost an hour at the lowest listed on-demand price. Memory needed: 698 GB at 16-bit, 349 GB at 8-bit, 175 GB at 4-bit.

| Accelerator | Memory per card | Lowest price per card | 16-bit | 8-bit | 4-bit |
| --- | --- | --- | --- | --- | --- |
| [H100](https://savrn.com/ai-index/pricing/gpus/h100) Voltage Park | 80 GB | $1.99 | More than 8 | 5 cards $9.95/hr | 3 cards $5.97/hr |
| [H200](https://savrn.com/ai-index/pricing/gpus/h200) GMI Cloud | 141 GB | $2.60 | 5 cards $13.00/hr | 3 cards $7.80/hr | 2 cards $5.20/hr |
| [B200](https://savrn.com/ai-index/pricing/gpus/b200) Vultr | 180 GB | $3.50 | 4 cards $14.00/hr | 2 cards $7.00/hr | 1 card $3.50/hr |
| [GB200 NVL72](https://savrn.com/ai-index/pricing/gpus/gb200) GMI Cloud | 186 GB | $8.00 | 4 cards $32.00/hr | 2 cards $16.00/hr | 1 card $8.00/hr |
| [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) Vultr | 192 GB | $1.85 | 4 cards $7.40/hr | 2 cards $3.70/hr | 1 card $1.85/hr |
| [MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) Vultr | 256 GB | $2.00 | 3 cards $6.00/hr | 2 cards $4.00/hr | 1 card $2.00/hr |
| [B300](https://savrn.com/ai-index/pricing/gpus/b300) Massed Compute | 268 GB | $6.60 | 3 cards $19.80/hr | 2 cards $13.20/hr | 1 card $6.60/hr |
| [GB300 NVL72](https://savrn.com/ai-index/pricing/gpus/gb300) Verda | 279 GB | $11.94 | 3 cards $35.82/hr | 2 cards $23.88/hr | 1 card $11.94/hr |
| [MI355X](https://savrn.com/ai-index/pricing/gpus/mi355x) Vultr | 288 GB | $2.59 | 3 cards $7.77/hr | 2 cards $5.18/hr | 1 card $2.59/hr |

## Running It Around the Clock

| Precision | Cheapest setup | Per hour | Per month (730 hours) |
| --- | --- | --- | --- |
| 16-bit | 3x [MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) (Vultr) | $6.00 | $4,380 |
| 8-bit | 2x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (Vultr) | $3.70 | $2,701 |
| 4-bit | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (Vultr) | $1.85 | $1,350 |

One copy of the model on rented cards, busy or idle. Serving more users at once takes more copies or more memory for their contexts.

## Questions

### How much VRAM does DeepSeek-V4-Flash need?

About 698 GB at 16-bit; about 349 GB at 8-bit; about 175 GB at 4-bit: the weights plus 20% for the runtime and a short context. A long context needs more.

### What is the cheapest GPU setup to run DeepSeek-V4-Flash?

At 16-bit, 3x MI325X from $6.00 an hour, at the lowest on-demand price the SAVRN Index lists.

### Can DeepSeek-V4-Flash run on a single H100?

No. An H100 has 80 GB, and DeepSeek-V4-Flash needs 175 GB even at 4-bit, so it takes more than one card.

Memory is the weights at that precision plus 20% for the runtime and a short context. Prices are the lowest on-demand hourly rates in the [SAVRN Index](https://savrn.com/ai-index/pricing/gpus), read Oct 24, 2026. Setups beyond eight cards, one server, are not listed.

## DeepSeek-V4-Flash

- [Model card, license and download](https://savrn.com/models/deepseek-v4-flash)
- [All text generation models](https://savrn.com/models/tasks/text-generation)
- [GPU prices in the SAVRN Index](https://savrn.com/ai-index/pricing/gpus)