R1 1776 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 R1 1776?
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
- Perplexity
- Organisation type
- Industry
- Country
- United States of America
- Published
- 18 February 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, Question answering, Chat
- Base model
- DeepSeek-R1
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 params
40k multilingual prompts assuming ~1000 tokens per prompt -> 40M tokens
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.
- How it was established
- Operation counting
- Fine-tuning compute
- 8.9 × 10¹⁸ FLOP
Deepseek R1 has 37B active parameters fine-tuning dataset is speculatively estimated to be 40M tokens (see dataset size notes) 6 FLOP / token / parameter * 37 * 10^9 paramters * 40*10^6 tokens = 8.88e+18 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
- Hugging Face
- perplexity-ai
MIT license https://huggingface.co/perplexity-ai/r1-1776
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Speculative
Sources
Where this record came from and when it was last checked.
- Reference
- Open-sourcing R1 1776
- Last updated
- 28 November 2025
What the numbers mean
Hardware requirements in practice
At 671B parameters, R1 1776 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
R1 1776 was published by Perplexity, in United States of America, in February 2025. industry is the category the publisher falls under.
It works in Language, and is recorded as doing language modeling/generation, Question answering, Chat.
It builds on DeepSeek-R1, 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 perplexity-ai organisation on Hugging Face.
Step by step
How to choose a GPU for R1 1776
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
The table lists every card that can hold R1 1776. That figure, not the card's headline performance, is what decides whether it runs.
-
02
Set the context length you will work at
The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context R1 1776 can slip off a card that handles short questions easily.
-
03
Choose how far you will compress it
Compression is what makes R1 1776 fit smaller cards, at some cost in accuracy. A minimum quality removes the ones that go too far.
-
04
Compare tokens per second, not specifications
Sort by speed to see how cards rank for R1 1776. It will not match a gaming ordering — generation is bound by memory bandwidth.
-
05
Look at the headroom, not just the fit
The fit column separates cards that just manage R1 1776 from those with room to spare. Buy for the second if the context might grow.
-
06
Check the card from the other side
Following a card through to its own page shows every other model it can hold, which is the question that follows once R1 1776 is settled.
Answers
R1 1776 — common questions
Can I run R1 1776 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 R1 1776 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 R1 1776 faster?
A second card roughly doubles the memory available but not the generation rate. With 0 cards already able to run R1 1776 alone, the case for pairing is weak.
Why does the quantisation differ between cards for R1 1776?
Because capacity varies, so does how hard R1 1776 has to be squeezed — 1 distinct levels appear in the table above. Set a minimum quality to compare at one.
How accurate are these R1 1776 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 R1 1776 open source?
Its weights are published, so R1 1776 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 R1 1776 have?
R1 1776 has 671B parameters. 671B params. 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 R1 1776?
R1 1776 was published by Perplexity, based in United States of America, categorised as industry.
When was R1 1776 released?
R1 1776 was published in February 2025.
What is R1 1776 used for?
R1 1776 works in Language, and is recorded as handling language modeling/generation, Question answering, Chat. 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 R1 1776?
Its weights are published under the perplexity-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.