MAI-DS-R1 TPS calculator

Open weights Microsoft 671B parameters April 2025

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

0 cards that can run it

818 cards we hold specifications for

Which GPUs can run MAI-DS-R1?

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
Microsoft
Organisation type
Industry
Country
United States of America
Published
16 April 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, Quantitative reasoning, Code generation
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

671B MoE

Training data
tokens

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

MIT license https://huggingface.co/microsoft/MAI-DS-R1

Hugging Face
microsoft

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
MAI-DS-R1 is a DeepSeek-R1 reasoning model that has been post-trained by the Microsoft AI team to improve its responsiveness on blocked topics and its risk profile, while maintaining its reasoning capabilities and competitive performance.
Last updated
28 November 2025

What the numbers mean

The hardware side

MAI-DS-R1 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

MAI-DS-R1 was published by Microsoft, in the country recorded as United States of America, during April 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, Question answering, Quantitative reasoning, Code generation.

Rather than being trained from scratch, it is derived from DeepSeek-R1. That is the usual way a specialised model is produced.

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 microsoft.

Step by step

How to choose a GPU for MAI-DS-R1

The table above has already assessed every card we hold specifications for against this model. Getting to your answer takes six steps.

  1. 01

    Read the memory figure first

    Every card here has been checked against MAI-DS-R1. Capacity is the gate — a card either holds it or it does not.

  2. 02

    Match the context to your actual use

    Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for MAI-DS-R1.

  3. 03

    Choose how far you will compress it

    Each card runs the least-compressed copy it can hold. 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.

  4. 04

    Rank by throughput rather than spec sheet

    The speed ordering is effectively an ordering by memory bandwidth, for MAI-DS-R1. It will not match a gaming ordering, because generation is bound by memory bandwidth.

  5. 05

    Look at the headroom, not just the fit

    Tight means it loads and works with no room to raise the context later, in the case of MAI-DS-R1. 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.

  6. 06

    See what else that card runs

    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 MAI-DS-R1.

Answers

MAI-DS-R1 — common questions

01

MAI-DS-R1— how accurate are these speed estimates?

These are estimates with real error bars, and any of them could reasonably land anywhere in its published range depending on which runtime you use. The fastest result here: 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.

02

MAI-DS-R1— 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.

03

MAI-DS-R1— how many parameters does it have?

It has a parameter count of 671B. 671B MoE. 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.

04

MAI-DS-R1— who created it?

It was published by Microsoft, based in United States of America, an organisation categorised as industry.

05

MAI-DS-R1— when was it released?

It was published in April 2025.

06

MAI-DS-R1— 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, Quantitative reasoning, Code generation. 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.

07

MAI-DS-R1— where can I download it?

Its weights are published on Hugging Face, under the organisation microsoft. We do not host model files — this site calculates what hardware is needed to run them.

08

MAI-DS-R1— 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.

09

MAI-DS-R1— 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.

10

MAI-DS-R1— 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.

Source

Original publication

Record last updated 28 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.