DeepSeek-R1 TPS calculator
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
818 cards we hold specifications for
Which GPUs can run DeepSeek-R1?
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
- 20 January 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
- Base model
- DeepSeek-V3
- Numerical format
- FP8
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
- Training data
- 14,800,000,000,000 tokens
671B total 37B activated https://github.com/deepseek-ai/DeepSeek-R1/tree/main
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
- 3.5 × 10²⁴ FLOP
- How it was established
- Operation counting
- Fine-tuning compute
- 1.8 × 10²³ FLOP
3.29e24 + 1.8e23 = 3.47e24, round to 3.5e24 due to lack of sigfigs
H800 throughput is 1.5e15 FLOPs, and implied MFU is 23% 147k H800 GPU-hours is 147k * 3600 s/hr * 1.5e15 * 0.23 = 1.83e23 FLOP
The training run
What it physically took to train: which chips, how many, for how long, and what that drew from the wall.
- Compute cost
- $6,770,000
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
- Hugging Face
- deepseek-ai
MIT licensed https://huggingface.co/deepseek-ai/DeepSeek-R1
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
- Why it is tracked
- Training cost,SOTA improvement
- Record confidence
- Confident
Best score on SuperCLUE Math6o in Jan 2025 https://www.superclueai.com/
Sources
Where this record came from and when it was last checked.
- Reference
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Last updated
- 20 January 2026
What the numbers mean
What it takes to run this model
At 671B parameters, DeepSeek-R1 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.
Where it came from
DeepSeek-R1 was published by DeepSeek, in China, in January 2025. industry is the category the publisher falls under.
It works in Language, and is recorded as doing language modeling/generation, Code generation, Quantitative reasoning, Question answering.
It builds on DeepSeek-V3, which is why it shares that model's general shape and size.
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.
What went into building it
Producing it required around 3.5 × 10²⁴ FLOP of arithmetic, which is a statement about the training budget rather than about inference.
Around 14,800,000,000,000 tokens went into training it.
Its inclusion criterion is training cost,SOTA improvement.
Step by step
How to choose a GPU for DeepSeek-R1
The table above has already assessed every card we hold specifications for against this model. Getting to your answer takes six steps.
-
01
Start from the memory column
Every card here has been checked against DeepSeek-R1. Capacity is the gate — a card either holds it or it does not.
-
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-R1 can slip off a card that handles short questions easily.
-
03
Choose how far you will compress it
Compression is what makes DeepSeek-R1 fit smaller cards, at some cost in accuracy. A minimum quality removes the ones that go too far.
-
04
Sort by speed
The speed ordering for DeepSeek-R1 is effectively an ordering by memory bandwidth.
-
05
Read the fit column last
Tight means DeepSeek-R1 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.
-
06
See what else that card runs
Every card name links to its own page, which runs the same calculation across the whole model catalogue. Worth a look before buying for DeepSeek-R1 alone — a card is usually bought for more than one model.
Answers
DeepSeek-R1 — common questions
How much compute was used to train DeepSeek-R1?
Around 3.5 × 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.
Can I run DeepSeek-R1 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-R1 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.
Would two GPUs run DeepSeek-R1 faster?
Capacity adds across cards; throughput does not. Since 0 of the cards we track already hold DeepSeek-R1 on their own, a second card is rarely the answer here.
Why does the quantisation differ between cards for DeepSeek-R1?
Each card is shown running the least-compressed copy it can hold, and DeepSeek-R1 appears at 1 different compression levels across the cards that fit it. Bigger cards get the more accurate version.
How accurate are these DeepSeek-R1 speed estimates?
Every figure is derived from memory bandwidth and model size, not benchmarked. That is why each is published as a range such as the range beneath each figure rather than a single number.
Is DeepSeek-R1 open source?
Its weights are published, so DeepSeek-R1 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.
How many parameters does DeepSeek-R1 have?
DeepSeek-R1 has 671B parameters. 671B total 37B activated https://github.com/deepseek-ai/DeepSeek-R1/tree/main. 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.
Who created DeepSeek-R1?
DeepSeek-R1 was published by DeepSeek, based in China, categorised as industry.
When was DeepSeek-R1 released?
DeepSeek-R1 was published in January 2025.
What is DeepSeek-R1 used for?
DeepSeek-R1 works in Language, and is recorded as handling language modeling/generation, Code generation, Quantitative reasoning, Question answering. 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.
Where can I download DeepSeek-R1?
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.
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.