MiniMax-M1-80k 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
Smallest card that fits
Radeon Instinct MI325X
256 GB · Q3_K_M · 11.7 tok/s
Fastest card
B300
18.3 tok/s · 288 GB
Which GPUs can run MiniMax-M1-80k?
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.
4 cards match
Calculating| Needs | Quantisation | Fit | |||||
|---|---|---|---|---|---|---|---|
|
18.3
tok/s
11–29 · low confidence |
B300 NVIDIA | 288 GB | 8,000 GB/s | Sep 2025 | 250.0 GB | IQ4_XS | Tight |
|
14.6
tok/s
9–23 · low confidence |
Radeon Instinct MI350X AMD | 288 GB | 8,190 GB/s | Jan 2025 | 250.0 GB | IQ4_XS | Tight |
|
14.6
tok/s
9–23 · low confidence |
Radeon Instinct MI355X AMD | 288 GB | 8,190 GB/s | Jan 2025 | 250.0 GB | IQ4_XS | Tight |
|
11.7
tok/s
7–19 · low confidence |
Radeon Instinct MI325X AMD | 256 GB | 6,000 GB/s | Oct 2024 | 223.5 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
- 13 June 2025
- Authors
- MiniMax: Aili Chen, Aonian Li, Bangwei Gong, Binyang Jiang, Bo Fei, Bo Yang, Boji Shan, Changqing Yu, Chao Wang, Cheng Zhu, Chengjun Xiao, Chengyu Du, Chi Zhang, Chu Qiao, Chunhao Zhang, Chunhui Du, Congchao Guo, Da Chen, Deming Ding, Dianjun Sun, Dong Li, Enwei Jiao, Haigang Zhou, Haimo Zhang, Han Ding, Haohai Sun, Haoyu Feng, Huaiguang Cai, Haichao Zhu, Jian Sun, Jiaqi Zhuang, Jiaren Cai, Jiayua…
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, Code generation, Quantitative reasoning
- Base model
- MiniMax-Text-01
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
- 456B
- Training data
- 7,500,000,000,000 tokens
from the base model: Total Parameters: 456B Activated Parameters per Token: 45.9B
7.5T tokens "To enhance the reasoning and long context capabilities of the foundation model while ensuring diversity, we continue training the MiniMax-Text-01 model with additional 7.5T tokens with optimized data quality and mixture."
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
- 4.3 × 10²⁴ FLOP
- Fine-tuning compute
- 2.3 × 10²⁴ FLOP
1.9828799999999997e+24 FLOP [base model compute] + 2.3411262e+24 FLOP [see finetune compute notes] = 4.3240062e+24 FLOP
1. Continual pre-training for 7.5T tokens: 6 FLOP / token / active parameter * 45.9 * 10^9 activated parameters * 7.5 * 10^12 tokens = 2.0655e+24 FLOP 2. RL (3 weeks on 512 H800 GPUs): 989000000000000 FLOP / GPU / sec [bf16 assumed] * 512 GPUs * 3 weeks * 168 hours / week * 3600 sec / hour * 0.3 [assimed utilization] = 2.7562623e+23 FLOP 2.0655e+24 FLOP + 2.7562623e+23 FLOP = 2.3411262e+24 FLOP *there was also SFT stage with no details provided, I assumed its compute is negligible
The training run
What it physically took to train: which chips, how many, for how long, and what that drew from the wall.
- Training hardware
- NVIDIA H800 SXM5
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
Apache 2.0 https://huggingface.co/MiniMaxAI/MiniMax-M1-80k
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Likely
Sources
Where this record came from and when it was last checked.
- Reference
- MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention
- Last updated
- 28 November 2025
The extremes
The ten fastest GPUs for MiniMax-M1-80k
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-M1-80k
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 MI325X
Memory needed
223.5 GB
Fastest
18.3 tok/s
At 456B parameters, MiniMax-M1-80k is beyond what any single graphics card holds. Running it means either splitting it across several cards or renting hardware built for the job — 4 of the cards we track can hold it on their own, and all of them are datacentre parts.
The entry point is the Radeon Instinct MI325X: 256 GB of memory, Q3_K_M compression, roughly 11.7 tokens per second.
Top of the range is the B300, at roughly 18.3 tokens per second thanks to 8,000 GB/s of bandwidth.
What this model is
MiniMax-M1-80k was published by MiniMax, in China, in June 2025. It comes out of industry.
It works in Language, and is recorded as doing language modeling/generation, Question answering, Code generation, Quantitative reasoning.
Its starting point was MiniMax-Text-01 — most models at this scale are adapted from an existing base rather than built from nothing.
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 MiniMaxAI organisation on Hugging Face.
What decides the speed
Across every card that can run it, the middle of the range is about 14.6 tokens per second, and 4 of them clear the ten tokens per second that roughly matches reading speed.
It is a dense model, so every parameter is read for every token produced. That makes speed track memory bandwidth almost exactly — a card with twice the bandwidth generates roughly twice as fast.
Without the attention layout on record, the memory column is an approximation. It is close enough to choose hardware by, and least reliable at long context.
How it was trained
Producing it required around 4.3 × 10²⁴ FLOP of arithmetic, on NVIDIA H800 SXM5, which is a statement about the training budget rather than about inference.
The training set ran to roughly 7,500,000,000,000 tokens.
Step by step
How to choose a GPU for MiniMax-M1-80k
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
Look at what MiniMax-M1-80k actually needs — around 223.5 GB at Q3_K_M. No amount of processing power compensates for a card that cannot hold it.
-
02
Match the context to your actual use
Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason MiniMax-M1-80k stops fitting a card that seemed fine.
-
03
Decide how much compression you will accept
Compression is what makes MiniMax-M1-80k fit smaller cards, at some cost in accuracy — Q3_K_M on the smallest card that fits. A minimum quality removes the ones that go too far.
-
04
Rank by throughput rather than spec sheet
Sort by speed to see how cards rank for MiniMax-M1-80k. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B300 tops it at 18.3 tok/s.
-
05
Look at the headroom, not just the fit
A tight fit runs MiniMax-M1-80k but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.
-
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 MiniMax-M1-80k is settled.
Answers
MiniMax-M1-80k — common questions
Who created MiniMax-M1-80k?
MiniMax-M1-80k was published by MiniMax, based in China, categorised as industry.
When was MiniMax-M1-80k released?
MiniMax-M1-80k was published in June 2025.
What is MiniMax-M1-80k used for?
MiniMax-M1-80k works in Language, and is recorded as handling language modeling/generation, Question answering, Code generation, Quantitative reasoning. These are the areas it was designed around; they describe intent rather than a hard boundary.
Where can I download MiniMax-M1-80k?
Its weights are published under the MiniMaxAI organisation on Hugging Face. We do not host model files — this site calculates what hardware is needed to run them.
How much compute was used to train MiniMax-M1-80k?
Around 4.3 × 10²⁴ FLOP, on NVIDIA H800 SXM5. 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.
Can I run MiniMax-M1-80k 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 MiniMax-M1-80k is rarely worth using — the nearest miss we calculate is short by 103.8 GB. Every figure here assumes the whole model is on the card.
Would two GPUs run MiniMax-M1-80k faster?
A second card roughly doubles the memory available but not the generation rate. With 4 cards already able to run MiniMax-M1-80k alone, the case for pairing is weak.
Why does the quantisation differ between cards for MiniMax-M1-80k?
A larger card holds a more accurate copy. Across the cards that run MiniMax-M1-80k, 2 compression levels are used; the floor control above pins it to one.
How accurate are these MiniMax-M1-80k speed estimates?
They are calculated from specifications rather than measured, and each carries a range — 11–29 tok/s on the B300, for instance. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.
What GPU do I need to run MiniMax-M1-80k?
The smallest card in our catalogue that holds MiniMax-M1-80k is the Radeon Instinct MI325X, with 256 GB of memory. It runs the model at Q3_K_M using about 223.5 GB, and produces roughly 11.7 tokens per second. 4 cards in total can run it.
How fast is MiniMax-M1-80k on a GPU?
It depends on the card. The quickest we calculate is a B300 at about 18.3 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 4 of the cards that can run MiniMax-M1-80k clear that.
How much VRAM does MiniMax-M1-80k need?
About 223.5 GB at Q3_K_M compression, 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.
Is MiniMax-M1-80k open source?
Its weights are published, so MiniMax-M1-80k 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 MiniMax-M1-80k have?
MiniMax-M1-80k has 456B parameters. from the base model: Total Parameters: 456B Activated Parameters per Token: 45.9B. 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.
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.