DeepSeek-Prover-V2-671B TPS calculator

Open weights DeepSeek 671B parameters April 2025

Each card below is assessed against this model at the context length and minimum quality you choose. Speed is an estimate for a single request, calculated from the card's memory bandwidth and the size of the model once compressed.

Calculated for this model

0 cards that can run it

818 cards we hold specifications for

Which GPUs can run DeepSeek-Prover-V2-671B?

Set the inputs, read the answer

A longer conversation needs more memory, which can push this model off smaller cards.

Hides cards that would only fit the model by compressing it below this point.

0 cards match

Calculating
Needs Quantisation Fit

No card in our catalogue can run this model with these settings.

Speeds are estimates for a single request — one conversation at a time — calculated from memory bandwidth, model size and quantisation. Real throughput varies with the inference runtime and its version. Figures published by hardware vendors measure many simultaneous requests and are much higher.

On record

Full specification

Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.

Origin

Who built this model, where, and when it was published.

Organisation
DeepSeek
Organisation type
Industry
Country
China
Published
30 April 2025
Authors
Z.Z. Ren, Zhihong Shao, Junxiao Song, Huajian Xin, Haocheng Wang, Wanjia Zhao, Liyue Zhang, Zhe Fu, Qihao Zhu, Dejian Yang, Z.F. Wu, Zhibin Gou, Shirong Ma, Hongxuan Tang, Yuxuan Liu, Wenjun Gao, Daya Guo, Chong Ruan

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Language
Task
Language modeling/generation, Question answering, Quantitative reasoning, Mathematical reasoning
Base model
DeepSeek-V3

Size

How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.

Parameters
671B

671B

Training data
tokens

Availability

Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.

Weights
Open — downloadable
Model access
Open weights (restricted use)
Training code
Unreleased

Deepseek Model License: Deepseek Model License: "DeepSeek reserves the right to restrict (remotely or otherwise) usage of the Model" https://github.com/deepseek-ai/DeepSeek-V3/blob/main/LICENSE-MODEL https://huggingface.co/deepseek-ai/DeepSeek-Prover-V2-671B

Hugging Face
deepseek-ai

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Likely above 10²³ FLOP
Yes
Record confidence
Confident

Sources

Where this record came from and when it was last checked.

Reference
DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition
Last updated
28 November 2025

What the numbers mean

What you need to run it

At 671B parameters, DeepSeek-Prover-V2-671B is beyond what any single graphics card holds. Running it means either splitting it across several cards or renting hardware built for the job — 0 of the cards we track can hold it on their own, and all of them are datacentre parts.

Background

DeepSeek-Prover-V2-671B was published by DeepSeek, in China, in April 2025. industry is the category the publisher falls under.

It works in Language, and is recorded as doing language modeling/generation, Question answering, Quantitative reasoning, Mathematical reasoning.

It is derived from DeepSeek-V3 rather than trained from scratch, which is the usual way a specialised model is produced.

Published weights mean the model runs on your machine rather than someone else's, which is what makes the hardware question below answerable at all. It is published under the deepseek-ai organisation on Hugging Face.

Step by step

How to choose a GPU for DeepSeek-Prover-V2-671B

The table above has already assessed every card we hold specifications for against this model. Getting to your answer takes six steps.

  1. 01

    Check what it needs before anything else

    Every card here has been checked against DeepSeek-Prover-V2-671B. Capacity is the gate — a card either holds it or it does not.

  2. 02

    Decide how long your conversations run

    The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context DeepSeek-Prover-V2-671B can slip off a card that handles short questions easily.

  3. 03

    Set a quality floor

    Each card runs the least-compressed copy it can hold. Setting a floor drops the cards that only manage DeepSeek-Prover-V2-671B by squeezing it further than you would want.

  4. 04

    Compare tokens per second, not specifications

    Ranking by tokens per second for DeepSeek-Prover-V2-671B follows memory bandwidth, not core counts.

  5. 05

    Read the fit column last

    Tight means DeepSeek-Prover-V2-671B loads and works, with no room to raise the context later. Comfortable means you can. The difference matters more than a few tokens per second.

  6. 06

    Open the card you have settled on

    Each card page repeats this sweep for every model we hold. It answers what else the hardware is good for, beyond DeepSeek-Prover-V2-671B.

Answers

DeepSeek-Prover-V2-671B — common questions

01

Is DeepSeek-Prover-V2-671B open source?

Its weights are published, so DeepSeek-Prover-V2-671B can be downloaded and run on your own hardware. Note that open weights is not the same as open source in the full sense — it says nothing about the training data, the training code, or the commercial terms attached.

02

How many parameters does DeepSeek-Prover-V2-671B have?

DeepSeek-Prover-V2-671B has 671B parameters. 671B. That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.

03

Who created DeepSeek-Prover-V2-671B?

DeepSeek-Prover-V2-671B was published by DeepSeek, based in China, categorised as industry.

04

When was DeepSeek-Prover-V2-671B released?

DeepSeek-Prover-V2-671B was published in April 2025.

05

What is DeepSeek-Prover-V2-671B used for?

DeepSeek-Prover-V2-671B works in Language, and is recorded as handling language modeling/generation, Question answering, Quantitative reasoning, Mathematical reasoning. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

06

Where can I download DeepSeek-Prover-V2-671B?

Its weights are published under the deepseek-ai organisation on Hugging Face. We do not host model files — this site calculates what hardware is needed to run them.

07

Can I run DeepSeek-Prover-V2-671B if it does not fit in my GPU?

Partly. Layers that do not fit sit in system memory and run at a fraction of the speed, so a mostly-offloaded DeepSeek-Prover-V2-671B is rarely worth using — the nearest miss we calculate is short by 147.5 GB. Every figure here assumes the whole model is on the card.

08

Would two GPUs run DeepSeek-Prover-V2-671B faster?

A second card roughly doubles the memory available but not the generation rate. With 0 cards already able to run DeepSeek-Prover-V2-671B alone, the case for pairing is weak.

09

Why does the quantisation differ between cards for DeepSeek-Prover-V2-671B?

A larger card holds a more accurate copy. Across the cards that run DeepSeek-Prover-V2-671B, 1 compression levels are used; the floor control above pins it to one.

10

How accurate are these DeepSeek-Prover-V2-671B speed estimates?

They are calculated from specifications rather than measured, and each carries a range — the range beneath each figure, for instance. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

Source

Original publication

Record last updated 28 November 2025

The other direction

Looking at it from the other side?

This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.