DeepSeek-V3.1 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 DeepSeek-V3.1?
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
- DeepSeek
- Organisation type
- Industry
- Country
- China
- Published
- 21 August 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, Search, System control, Instruction interpretation
- 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
- 840,000,000,000 tokens
671B total, 37B active
"840B tokens continued pretraining for long context extension on top of V3" "The 32K extension phase has been increased 10-fold to 630B tokens, while the 128K extension phase has been extended by 3.3x to 209B tokens." 839B in total
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
- 3.6 × 10²⁴ FLOP
- How it was established
- Operation counting
- Fine-tuning compute
- 1.9 × 10²³ FLOP
This was based on V3 which was trained on 14.8T tokens for a total of 14.8T + 840B = 15.64T pretraining tokens. Adding the FLOPs from continued pretraining onto our estimate for V3, which is 3.4e24 FLOPs, we get 3.4e24 + 1.9e23 = 3.59e24
6 FLOP / parameter / token * 37* 10^9 active parameters * 839 * 10^9 tokens = 1.86258e+23 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
- deepseek-ai
MIT license https://huggingface.co/deepseek-ai/DeepSeek-V3.1
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 DeepSeek-V3.1: our first step toward the agent era!
- Last updated
- 20 January 2026
What the numbers mean
What you need to run it
DeepSeek-V3.1 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.
About this model
DeepSeek-V3.1 was published by DeepSeek, in the country recorded as China, during August 2025. The publishing organisation is categorised as 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, Search, System control, Instruction interpretation.
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.
Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded. On Hugging Face it is published under the organisation deepseek-ai.
Training and provenance
The training run consumed about 3.6 × 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 840,000,000,000 tokens of text.
Step by step
How to choose a GPU for DeepSeek-V3.1
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
The table lists every card able to hold DeepSeek-V3.1. Capacity is the gate — a card either holds it or it does not.
-
02
Match the context to your actual use
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 DeepSeek-V3.1.
-
03
Set a quality floor
The quantisation column varies by card, because a bigger card holds a more accurate copy. 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
Sort by speed
Sort by speed to see how cards rank for DeepSeek-V3.1. It will not match a gaming ordering, because generation is bound by memory bandwidth.
-
05
Read the fit column last
Tight means it loads and works with no room to raise the context later, in the case of DeepSeek-V3.1. 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
Each card page repeats this sweep for every model we hold, answering what else the hardware is good for beyond DeepSeek-V3.1.
Answers
DeepSeek-V3.1 — common questions
DeepSeek-V3.1— when was it released?
It was published in August 2025.
DeepSeek-V3.1— 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, Search, System control, Instruction interpretation. These are the areas it was designed around; they describe intent rather than a hard boundary.
DeepSeek-V3.1— 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-V3.1— how much compute was used to train it?
Training consumed around 3.6 × 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-V3.1— 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 103.0 GB. Every figure here assumes the whole model is resident on the card.
DeepSeek-V3.1— would two GPUs run it faster?
Two cards buy memory rather than speed, which matters only if one card cannot hold it. The number that can: 0. So a second card is rarely the answer here.
DeepSeek-V3.1— 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.
DeepSeek-V3.1— 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.
DeepSeek-V3.1— 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.
DeepSeek-V3.1— 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.
DeepSeek-V3.1— who created it?
It was published by DeepSeek, based in China, an organisation 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.