Cogito v2.1 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 Cogito v2.1?
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
- Deep Cogito
- Published
- 19 November 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
- Base model
- DeepSeek-V3-Base
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 active
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)
- Hugging Face
- deepcogito
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Confident
Sources
Where this record came from and when it was last checked.
- Reference
- Introducing Cogito v2.1
- Last updated
- 11 August 2026
What the numbers mean
Hardware requirements in practice
Cogito v2.1 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
Cogito v2.1 was published by Deep Cogito, during November 2025.
It works in the domain of Language, and is recorded as performing the task of language modeling/generation, Question answering.
It builds on DeepSeek-V3-Base. That is why it shares the base model's general shape and size.
The weights being open is what puts this page in the calculator rather than only in the catalogue: it is a model you can actually hold. On Hugging Face it is published under the organisation deepcogito.
Step by step
How to choose a GPU for Cogito v2.1
The table above has already assessed every card we hold specifications for against this model. Getting to your answer takes six steps.
-
01
Check what it needs before anything else
Every card here has been checked against Cogito v2.1. That figure, not the headline performance of a card, is what decides whether it runs.
-
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, because at long context a card that handles short questions easily can be dropped by Cogito v2.1.
-
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
Rank by throughput rather than spec sheet
Sort by speed to see how cards rank for Cogito v2.1. It will not match a gaming ordering, because generation is bound by memory bandwidth.
-
05
Read the fit column last
A tight fit runs, but leaves nothing spare for a longer conversation, in the case of Cogito v2.1. 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
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 you have settled on Cogito v2.1.
Answers
Cogito v2.1 — common questions
Cogito v2.1— what is it used for?
It works in the domain of Language, and is recorded as handling the task of language modeling/generation, 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.
Cogito v2.1— where can I download it?
Its weights are published on Hugging Face, under the organisation deepcogito. We do not host model files — this site calculates what hardware is needed to run them.
Cogito v2.1— 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.
Cogito v2.1— 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.
Cogito v2.1— why does the quantisation differ between cards?
Because capacity varies, so does how hard it has to be squeezed. The number of distinct levels in the table above: 1. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.
Cogito v2.1— 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.
Cogito v2.1— 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.
Cogito v2.1— 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.
Cogito v2.1— who created it?
It was published by Deep Cogito.
Cogito v2.1— when was it released?
It was published in November 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.