DeepSeek-V3.1-Terminus TPS calculator

Open weights DeepSeek 671B parameters September 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-V3.1-Terminus?

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
22 September 2025

What it does

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

Domain
Language
Task
Language modeling/generation, Code generation, Quantitative reasoning, Question answering, Search, System control, Instruction interpretation
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 total, 37B active

Training data
839,000,000,000 tokens

From V3.1 training dataset information: "840B tokens continued pretraining for long context extension on top of V3" "The 32K extension phase has been increased 10-fold to 630B tokens, while the 128K extension phase has been extended by 3.3x to 209B tokens." 839B in total

Training compute

The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.

Training compute
3.6 × 10²⁴ FLOP

This was based on V3 which was trained on 14.8T tokens for a total of 14.8T + 840B = 15.64T pretraining tokens. Adding the FLOPs from continued pretraining onto our estimate for V3, which is 3.4e24 FLOPs, we get 3.4e24 + 1.9e23 = 3.59e24

How it was established
Operation counting
Fine-tuning compute
1.9 × 10²³ FLOP

6 FLOP/parameter/token * 671000000000 parameters * 839000000000 tokens = 3.377814e+24 FLOP

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 (unrestricted)
Training code
Unreleased

MIT license https://huggingface.co/deepseek-ai/DeepSeek-V3.1-Terminus

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.

Record confidence
Likely

Sources

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

Reference
The latest update builds on V3.1’s strengths while addressing key user feedback.
Last updated
20 January 2026

What the numbers mean

The hardware side

DeepSeek-V3.1-Terminus reaches a parameter count of 671B. That is beyond what any single graphics card holds. Running it means either splitting it across several cards or renting hardware built for the job, and every card able to hold it alone is a datacentre part. The number that can: 0.

Where it came from

DeepSeek-V3.1-Terminus was published by DeepSeek, in the country recorded as China, during September 2025. It comes out of an organisation categorised as industry.

It works in the domain of Language, and is recorded as performing the task of language modeling/generation, Code generation, Quantitative reasoning, Question answering, Search, System control, Instruction interpretation.

It builds on DeepSeek-V3. Most models at this scale are adapted from an existing base rather than built from nothing.

The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached. On Hugging Face it is published under the organisation deepseek-ai.

What went into building it

Producing it required arithmetic totalling around 3.6 × 10²⁴ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.

Training consumed a corpus of around 839,000,000,000 tokens of text.

Step by step

How to choose a GPU for DeepSeek-V3.1-Terminus

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

    Start from what it actually needs, which is the requirement of DeepSeek-V3.1-Terminus. That figure, not the headline performance of a card, is what decides whether it runs.

  2. 02

    Set the context length you will work at

    Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason a card that seemed fine stops fitting DeepSeek-V3.1-Terminus.

  3. 03

    Choose how far you will compress it

    Each card runs the least-compressed copy it can hold. Setting a minimum quality drops the cards that only manage it by squeezing further than you would want, and holds the comparison at one level.

  4. 04

    Sort by speed

    Sort by speed to see how cards rank for DeepSeek-V3.1-Terminus. It will not match a gaming ordering, because generation is bound by memory bandwidth.

  5. 05

    Check the fit verdict before buying

    Tight means it loads and works with no room to raise the context later, in the case of DeepSeek-V3.1-Terminus. Comfortable means you can grow the context later. That difference matters more than a few tokens per second, so buy for comfortable if you expect to.

  6. 06

    Check the card from the other side

    Every card name links to its own page, which runs the same calculation across the whole model catalogue. A card is usually bought for more than one model, so it is worth a look before buying for DeepSeek-V3.1-Terminus.

Answers

DeepSeek-V3.1-Terminus — common questions

01

DeepSeek-V3.1-Terminus— how much compute was used to train it?

Training consumed around 3.6 × 10²⁴ FLOP. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.

02

DeepSeek-V3.1-Terminus— can I run it if it does not fit in my GPU?

Only by offloading, which is usually a false economy: the part held in system memory drags the whole thing down. The nearest miss we calculate falls short by 103.0 GB. Every figure here assumes the whole model is resident on the card.

03

DeepSeek-V3.1-Terminus— would two GPUs run it faster?

A second card roughly doubles the memory available but not the generation rate. The number already able to run it alone: 0. So a second card is rarely the answer here.

04

DeepSeek-V3.1-Terminus— why does the quantisation differ between cards?

A larger card holds a more accurate copy. The number of compression levels used across the cards that run it: 1. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

05

DeepSeek-V3.1-Terminus— how accurate are these speed estimates?

Every figure is derived from memory bandwidth and model size, not benchmarked, which is why each is published as a range rather than a single number. One example: the range beneath each figure. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

06

DeepSeek-V3.1-Terminus— is it open source?

Its weights are published, so it 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.

07

DeepSeek-V3.1-Terminus— how many parameters does it have?

It has a parameter count of 671B. 671B total, 37B active. 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.

08

DeepSeek-V3.1-Terminus— who created it?

It was published by DeepSeek, based in China, an organisation categorised as industry.

09

DeepSeek-V3.1-Terminus— when was it released?

It was published in September 2025.

10

DeepSeek-V3.1-Terminus— what is it used for?

It works in the domain of Language, and is recorded as handling the task of language modeling/generation, Code generation, Quantitative reasoning, Question answering, Search, System control, Instruction interpretation. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

11

DeepSeek-V3.1-Terminus— where can I download it?

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

Source

Original publication

Record last updated 20 January 2026

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.