DeepSeek-R1-Zero 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-Zero?
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
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
- tokens
671B total 37B activated https://github.com/deepseek-ai/DeepSeek-R1/tree/main
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
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-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Last updated
- 28 November 2025
What the numbers mean
The hardware side
At 671B parameters, DeepSeek-R1-Zero 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.
About this model
DeepSeek-R1-Zero 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.
Step by step
How to choose a GPU for DeepSeek-R1-Zero
The table above has already assessed every card we hold specifications for against this model. Getting to your answer takes six steps.
-
01
Read the memory figure first
Look at what DeepSeek-R1-Zero actually needs. No amount of processing power compensates for a card that cannot hold it.
-
02
Decide how long your conversations run
Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason DeepSeek-R1-Zero stops fitting a card that seemed fine.
-
03
Choose how far you will compress it
The quantisation column varies by card, because a bigger card holds a more accurate copy of DeepSeek-R1-Zero. Set a floor to hold the comparison at one level.
-
04
Compare tokens per second, not specifications
The speed ordering for DeepSeek-R1-Zero is effectively an ordering by memory bandwidth.
-
05
Read the fit column last
Tight means DeepSeek-R1-Zero 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
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-R1-Zero.
Answers
DeepSeek-R1-Zero — common questions
When was DeepSeek-R1-Zero released?
DeepSeek-R1-Zero was published in January 2025.
What is DeepSeek-R1-Zero used for?
DeepSeek-R1-Zero 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-Zero?
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.
Can I run DeepSeek-R1-Zero if it does not fit in my GPU?
It can be split between the card and system memory, but DeepSeek-R1-Zero generates painfully slowly that way — the nearest miss we calculate is short by 147.5 GB. Nothing on this page assumes offloading.
Would two GPUs run DeepSeek-R1-Zero faster?
A second card roughly doubles the memory available but not the generation rate. With 0 cards already able to run DeepSeek-R1-Zero alone, the case for pairing is weak.
Why does the quantisation differ between cards for DeepSeek-R1-Zero?
Each card is shown running the least-compressed copy it can hold, and DeepSeek-R1-Zero 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-Zero 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.
Is DeepSeek-R1-Zero open source?
Its weights are published, so DeepSeek-R1-Zero 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-Zero have?
DeepSeek-R1-Zero 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-Zero?
DeepSeek-R1-Zero was published by DeepSeek, based in China, categorised as industry.
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.