Aiqre

Model library / deepseek-ai

DeepSeek-V4-Flash-0731

DeepSeek-V4-Flash-0731 is a 304.2 billion-parameter, mixture-of-experts language model with speculative decoding for agentic tasks.

304.2B

6 of 256 experts active per token

1,048,576

Context length in tokens, as published

155 GiB

Weights at the released precision

mit

Licence declared on the repository

Overview

What this model is.

DeepSeek-V4-Flash-0731 is released by deepseek-ai as the official version of DeepSeek-V4-Flash, extending the preview model with enhanced agentic capabilities. The publisher describes it as suitable for code-agent tasks and general reasoning, offering a speculative decoding module (DSpark) and configurable reasoning effort levels. It is intended for use with OpenAI-compatible chat encoding and supports tool calling and reasoning features.

In practice the model comprises 304.2 billion parameters, organised as 256 experts with six active per token, and operates in fp8 format. It supports a context window of 1,048,576 tokens and is distributed under an MIT licence. Deployment requires handling the large size, using vLLM or SGLang with DSpark speculative decoding, and configuring sampling parameters such as temperature 1.0 and top_p 0.95.

Specification

The published shape.

Repositorydeepseek-ai/DeepSeek-V4-Flash-0731
Publisherdeepseek-ai
Published31 July 2026
ArchitectureDeepseekV4ForCausalLM
Model typedeepseek_v4
Parameters304,180,418,494
Experts256 total, 6 active per token
Layers43
Hidden size4,096
Attention heads64, 1 key/value heads
Context length1,048,576 tokens
Vocabulary129,280 tokens
Quantisationfp8
Licencemit

Memory

How much VRAM the weights need.

Parameter count multiplied by the bytes each format uses. The key-value cache comes on top.

PrecisionWeightsNotes
bf16566.6 GiBFull precision as released
fp8283.3 GiB8-bit, near-lossless on most models
int4141.6 GiB4-bit, smallest footprint

The cache costs 86 KiB per token at 16-bit, so the full 1,048,576-token context of one request needs about 86.0 GiB. Concurrency multiplies that number, not the weights.

That figure is an upper bound: this model uses sliding-window attention with a 128-token window on some layers, so long requests cache less than this.

Hardware

Which card runs it.

At the released precision, with 90% of the card given to the server and 2.5 GiB kept for the runtime. The context column is what is left for the cache on that setup.

GPUCards neededFree for cacheContext it holds
RTX 4090 24GB more than 8
RTX 5090 32GB 8 55.0 GiB about 670,388 tokens
L40S 48GB 4 7.4 GiB about 90,014 tokens
A100 80GB 4 122.6 GiB the full 1,048,576 tokens
H100 80GB 4 122.6 GiB the full 1,048,576 tokens
RTX PRO 6000 96GB 2 12.4 GiB about 150,977 tokens
H200 141GB 2 93.4 GiB the full 1,048,576 tokens

Serving

Running it yourself.

A vLLM launch line for the shape above. Check the model card for a runtime the publisher recommends.

vllm serve deepseek-ai/DeepSeek-V4-Flash-0731 \
  --tensor-parallel-size 8 \
  --max-model-len 667648 \
  --gpu-memory-utilization 0.90

Questions

The things people ask about this model.

How much GPU memory does DeepSeek-V4-Flash-0731 need?

The weights take about 155 GiB at the released precision. No single card in the table above holds that, so it needs several GPUs or a lower precision.

What licence does DeepSeek-V4-Flash-0731 use?

The repository declares mit. Read the licence text before commercial use: the name alone does not tell you what is allowed.

How long a context does it support?

The configuration allows 1,048,576 tokens. Whether the whole window is usable depends on the memory left for the cache, which the hardware table works out per card.

Can I use it through an API instead of hosting it?

This page is a reference, and Aiqre does not serve this model today. We deploy open-weight models on dedicated EU hardware on request, so if you want an OpenAI-compatible endpoint for it, email [email protected] with the model name and roughly what volume you expect.

Also in the library

Related models.

deepseek-ai/DeepSeek-V4-Pro-0813

DeepSeek-V4-Pro-0813 is a 1650.5B mixture-of-experts open-weight model published by deepseek-ai on Hugging Face. It uses the Deep…

nex-agi/Nex-N2.5-Pro

Nex-N2.5-Pro is a 396.8 billion-parameter MoE language model designed for long-horizon, agentic tasks with multimodal and compute…

ai-sage/GigaChat3.5-432B-A28B-Reasoning

GigaChat 3.5 Reasoning is a 438 billion-parameter mixture-of-experts language model trained with online RL for improved reasoning…

IFM/K2-Horizon-375B-A23B

K2-Horizon-375B-A23B is an open-weight sparse MiE language model from IFM with 379 B parameters, 23 B active per token and a 512 …

Hosting

Want this model on a dedicated EU GPU?

Tell us the model and roughly what volume you expect. We reply with a price and an OpenAI-compatible endpoint, with your prompts never stored.