MiniMax-M2 TPS calculator

Open weights MiniMax 229B parameters October 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

17 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Radeon Instinct MI250

128 GB · Q3_K_M · 12.8 tok/s

Fastest card

B200

34.2 tok/s · 180 GB

Which GPUs can run MiniMax-M2?

Set the inputs, read the answer

Context length tokens

A longer conversation needs more memory, which can push this model off smaller cards.

Minimum quality

Hides cards that would only fit the model by compressing it below this point.

Search cards

Card memory

Also show cards that cannot run it

17 cards match

Calculating

					Needs	Quantisation	Fit
34.2 tok/s 20–55 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	139.2 GB	Q4_K_M	Tight
25.5 tok/s 15–41 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	112.6 GB	Q3_K_M	Tight
22.2 tok/s 13–36 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	125.9 GB	IQ4_XS	Tight
22.2 tok/s 13–36 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	125.9 GB	IQ4_XS	Tight
20.7 tok/s 12–33 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	112.6 GB	Q3_K_M	Tight
14.8 tok/s 9–24 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	245.9 GB	Q8_0	Tight
13.7 tok/s 8–22 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	165.9 GB	Q5_K_M	Tight
13.7 tok/s 8–22 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	165.9 GB	Q5_K_M	Tight
12.8 tok/s 8–20 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	112.6 GB	Q3_K_M	Tight
12.8 tok/s 8–20 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	112.6 GB	Q3_K_M	Tight
12.6 tok/s 8–20 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	192.6 GB	Q6_K	Tight
11.8 tok/s 7–19 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	245.9 GB	Q8_0	Tight
11.8 tok/s 7–19 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	245.9 GB	Q8_0	Tight
10.6 tok/s 6–17 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	112.6 GB	Q3_K_M	Tight
10.4 tok/s 6–17 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	112.6 GB	Q3_K_M	Tight
1.4 tok/s 1–2 · low confidence	GB10 NVIDIA	128 GB	273 GB/s	Oct 2025	112.6 GB	Q3_K_M	Tight
1.4 tok/s 1–2 · low confidence	Jetson T5000 NVIDIA	128 GB	273 GB/s	Aug 2025	112.6 GB	Q3_K_M	Tight

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: MiniMax
Organisation type: Industry
Country: China
Published: 27 October 2025

What it does

The problem areas the model was built for. A model can carry several of each.

Domain: Language
Task: Code generation, System control, Search, Language modeling/generation, Question answering

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: 229B
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
Hugging Face: MiniMaxAI

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Why it is tracked: Discretionary
Record confidence: Confident

Sources

Where this record came from and when it was last checked.

Reference: MiniMax M2 & Agent: Ingenious in Simplicity
Last updated: 11 February 2026

The extremes

The ten fastest GPUs that run MiniMax-M2

Ranked by estimated tokens per second, newest card first where speeds tie. Because generation is bound by memory bandwidth, this ordering follows bandwidth rather than any gaming benchmark.

The smallest GPUs that still run MiniMax-M2

The cheapest route in, by memory capacity. A tight fit runs the model but leaves nothing spare for a longer conversation.

What the numbers mean

Hardware requirements in practice

Minimum card

Radeon Instinct MI250

Memory needed

112.6 GB

Fastest

34.2 tok/s

MiniMax-M2 reaches a parameter count of 229B. 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: 17.

The entry point is Radeon Instinct MI250, with a memory capacity of 128 GB, running it at a compression of Q3_K_M and producing around 12.8 tokens per second.

At the other end sits B200, generating roughly 34.2 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

Where it came from

MiniMax-M2 was published by MiniMax, in the country recorded as China, during October 2025. The category the publisher falls under is industry.

It works in the domain of Language, and is recorded as performing the task of code generation, System control, Search, Language modeling/generation, Question answering.

The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached. On Hugging Face it is published under the organisation MiniMaxAI.

Understanding the speeds

Across every card that can run it, the middle of the range sits at 12.8 tokens per second. Producing text faster than most people read it: 15 of them.

Every weight participates in every token here, so bandwidth is the whole story: the ranking below is effectively a ranking of memory throughput.

Its internal architecture is not on file, so memory is approximated from the parameter count and marked accordingly. Expect the real figure to differ, more so at long context.

What went into building it

The reason it appears in this catalogue at all: discretionary.

Step by step

How to choose a GPU for MiniMax-M2

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 MiniMax-M2, needing around 112.6 GB at a compression of Q3_K_M. No amount of processing power compensates for a card that cannot hold it.
02

Set the context length you will work at

Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for MiniMax-M2.
03

Set a quality floor

The quantisation column varies by card, because a bigger card holds a more accurate copy, reaching a compression of Q3_K_M on the smallest card that fits. 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

Ranking by tokens per second follows memory bandwidth rather than core counts, for MiniMax-M2. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 34.2 tok/s.
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 MiniMax-M2. 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

Open the card you have settled on

Each card page repeats this sweep for every model we hold, answering what else the hardware is good for beyond MiniMax-M2.

Answers

MiniMax-M2 — common questions

MiniMax-M2— what is it used for?

It works in the domain of Language, and is recorded as handling the task of code generation, System control, Search, 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.

MiniMax-M2— where can I download it?

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

MiniMax-M2— can I run it if it does not fit in my GPU?

It can be split between the card and system memory, but it generates painfully slowly that way. The nearest miss we calculate falls short by 52.8 GB. Every figure here assumes the whole model is resident on the card.

MiniMax-M2— 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: 17. So a second card is rarely the answer here.

MiniMax-M2— 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: 6. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

MiniMax-M2— 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: 20–55 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

MiniMax-M2— what GPU do I need to run it?

The smallest card in our catalogue that holds it is Radeon Instinct MI250, with a memory capacity of 128 GB. It runs the model at a compression of Q3_K_M using about 112.6 GB, and produces roughly 12.8 tokens per second. The number of cards able to run it in total: 17.

MiniMax-M2— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 34.2 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and the number of cards clearing that: 15.

MiniMax-M2— how much VRAM does it need?

It needs about 112.6 GB at a compression of Q3_K_M, which is what the smallest card that runs it uses. Less compression needs more: the figures in the memory column above are recalculated for each card, because each one holds the least-compressed version it can.

MiniMax-M2— 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.

MiniMax-M2— how many parameters does it have?

It has a parameter count of 229B. "maintaining activations around 10B" safetensors: 229B 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.

MiniMax-M2— who created it?

It was published by MiniMax, based in China, an organisation categorised as industry.

MiniMax-M2— when was it released?

It was published in October 2025.

Source

Original publication

Record last updated 11 February 2026

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.

All AI models