Arrakis / Models / DeepSeek-V4.1-Flash

DeepSeek-V4.1-Flash GPU requirements

DeepSeek-V4.1-Flash has 763B parameters. To serve it, plan for about 1,832 GB of GPU memory in 16-bit, 916 GB in 8-bit or 458 GB in 4-bit, including about 20% for the KV cache and activations.

It is a mixture of experts: 384 experts, 6 of them active for each token. All of them stay in GPU memory, so plan memory for all 763B parameters.

Deploy this model Check another model

What it takes to serve it

GPU memory to run it for inference, with the smallest GPU setup that holds it and the lowest price on Arrakis right now.

Precision	Memory and the smallest setup
16-bit	1,832 GB: 8 × B300, from $36.80 per hour for all 8
8-bit	916 GB: 4 × B300, from $18.40 per hour for all 4
4-bit	458 GB: 2 × B300, from $9.20 per hour for all 2

What it takes to fine-tune it

QLoRA trains adapters on a 4-bit frozen model, LoRA on a 16-bit one, and full fine-tuning updates every weight. Figures are before activations, which grow with batch size and sequence length.

Method	Memory and the smallest setup
QLoRA	534 GB: 4 × H200, from $13.76 per hour for all 4
LoRA	1,832 GB: 8 × B300, from $36.80 per hour for all 8
Full fine-tuning	12,211 GB: more than one 8-GPU machine

About the model

From its card and files on Hugging Face. Memory figures here follow the GPU memory guide.

Parameters: 763B
Experts: 384
Experts for each token: 6
Context window (tokens): 1,048,576
Published in: FP8
License: mit
Released: 2026-09-10
Weights: deepseek-ai/DeepSeek-V4.1-Flash

Deploy it on Arrakis

Open Models in the console, 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. Or run it yourself on any machine with enough GPU memory:

vLLM

vllm serve deepseek-ai/DeepSeek-V4.1-Flash --tensor-parallel-size 8

Deploy this model How deploying works

Questions

Live prices for every GPU are on the GPU prices page.

How much GPU memory does DeepSeek-V4.1-Flash need?

To serve it, about 1,832 GB in 16-bit, 916 GB in 8-bit, 458 GB in 4-bit, including about 20% for the KV cache and activations. To fine-tune it, about 534 GB with QLoRA, 1,832 GB with LoRA and 12,211 GB for full fine-tuning with Adam, before activations.

Can I run DeepSeek-V4.1-Flash on one GPU?

No. Even in 4-bit it needs about 458 GB: 2 B300 GPUs.

What does it cost to run DeepSeek-V4.1-Flash?

In 16-bit it needs 8 B300 GPUs; in 4-bit, 2 B300 GPUs. 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-V4.1-Flash on Arrakis?

Open Models in the Arrakis console, paste deepseek-ai/DeepSeek-V4.1-Flash, 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

Every model, and a check for any other.