DeepSeek-R1 (May 2025) 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 (May 2025)?
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
- 28 May 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
- 4 × 10²⁴ FLOP
- How it was established
- Operation counting
- Fine-tuning compute
- 6.1 × 10²³ FLOP
Estimates by Ege Erdil in Gradient Updates: https://epoch.ai/gradient-updates/what-went-into-training-deepseek-r1 "A dataset size of 14.8 trillion tokens is reasonable and in line with other models of this scale. Assuming that’s valid, the pretraining of this model would have required 6 * (37 billion) * (14.8 trillion) = 3e24 FLOP. If we assume DeepSeek’s training cluster consists of H800s with the PCIe form factor, then each should be capable of 1.5e15 FP8 per second, and the implied model FLOP…
6.1e23 FLOP from these estimations: https://epoch.ai/gradient-updates/what-went-into-training-deepseek-r1
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
- 11 February 2026
What the numbers mean
What it takes to run this model
DeepSeek-R1 (May 2025) 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.
Background
DeepSeek-R1 (May 2025) was published by DeepSeek, in the country recorded as China, during May 2025. The category the publisher falls under is 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.
Rather than being trained from scratch, it is derived from DeepSeek-V3. Most models at this scale are adapted from an existing base rather than built from nothing.
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. On Hugging Face it is published under the organisation deepseek-ai.
Training and provenance
Producing it required arithmetic totalling around 4 × 10²⁴ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.
It was trained on a corpus of about 14,800,000,000,000 tokens of text.
It is tracked in the underlying dataset for one reason in particular: training cost,SOTA improvement.
Step by step
How to choose a GPU for DeepSeek-R1 (May 2025)
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 (May 2025). Capacity is the gate — a card either holds it or it does not.
-
02
Decide how long your conversations run
Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for DeepSeek-R1 (May 2025).
-
03
Decide how much compression you will accept
Compression is what makes a model fit smaller cards, at some cost in accuracy. 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.
-
04
Compare tokens per second, not specifications
The speed ordering is effectively an ordering by memory bandwidth, for DeepSeek-R1 (May 2025). It will not match a gaming ordering, because generation is bound by memory bandwidth.
-
05
Read the fit column last
The fit column separates cards that just manage it from those with room to spare, in the case of DeepSeek-R1 (May 2025). 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.
-
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. A card is usually bought for more than one model, so it is worth a look before buying for DeepSeek-R1 (May 2025).
Answers
DeepSeek-R1 (May 2025) — common questions
DeepSeek-R1 (May 2025)— 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. These are the areas it was designed around; they describe intent rather than a hard boundary.
DeepSeek-R1 (May 2025)— 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.
DeepSeek-R1 (May 2025)— how much compute was used to train it?
Training consumed around 4 × 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.
DeepSeek-R1 (May 2025)— can I run it 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 model is rarely worth using. The nearest miss we calculate falls short by 147.5 GB. Every figure here assumes the whole model is resident on the card.
DeepSeek-R1 (May 2025)— 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.
DeepSeek-R1 (May 2025)— why does the quantisation differ between cards?
Each card is shown running the least-compressed copy it can hold. The number of distinct compression levels across the cards that fit it: 1. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.
DeepSeek-R1 (May 2025)— 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.
DeepSeek-R1 (May 2025)— 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.
DeepSeek-R1 (May 2025)— how many parameters does it have?
It has a parameter count of 671B. 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.
DeepSeek-R1 (May 2025)— who created it?
It was published by DeepSeek, based in China, an organisation categorised as industry.
DeepSeek-R1 (May 2025)— when was it released?
It was published in May 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.