MiniMax-VL-01 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
Smallest card that fits
Radeon Instinct MI325X
256 GB · IQ4_XS · 59.3 tok/s
Fastest card
B300
95.2 tok/s · 288 GB
Which GPUs can run MiniMax-VL-01?
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 | |||||
|---|---|---|---|---|---|---|---|
|
95.2
tok/s
57–152 · low confidence |
B300 NVIDIA | 288 GB | 8,000 GB/s | Sep 2025 | 252.1 GB | Q4_K_M | Tight |
|
76.1
tok/s
46–122 · low confidence |
Radeon Instinct MI350X AMD | 288 GB | 8,190 GB/s | Jan 2025 | 252.1 GB | Q4_K_M | Tight |
|
76.1
tok/s
46–122 · low confidence |
Radeon Instinct MI355X AMD | 288 GB | 8,190 GB/s | Jan 2025 | 252.1 GB | Q4_K_M | Tight |
|
59.3
tok/s
36–95 · low confidence |
Radeon Instinct MI325X AMD | 256 GB | 6,000 GB/s | Oct 2024 | 225.5 GB | IQ4_XS | 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
- 14 January 2025
- Authors
- MiniMax, Aonian Li, Bangwei Gong, Bo Yang, Boji Shan, Chang Liu, Cheng Zhu, Chunhao Zhang, Congchao Guo, Da Chen, Dong Li, Enwei Jiao, Gengxin Li, Guojun Zhang, Haohai Sun, Houze Dong, Jiadai Zhu, Jiaqi Zhuang, Jiayuan Song, Jin Zhu, Jingtao Han, Jingyang Li, Junbin Xie, Junhao Xu, Junjie Yan, Kaishun Zhang, Kecheng Xiao, Kexi Kang, Le Han, Leyang Wang, Lianfei Yu, Liheng Feng, Lin Zheng, Linbo Ch…
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Vision, Language, Multimodal
- Task
- Visual question answering, Language modeling/generation, Question answering
- 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
- 456.3B
- Training data
- tokens
"MiniMax-VL-01 undergoes additional training with 512 billion vision-language tokens"
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
- 2.1 × 10²⁴ FLOP
- How it was established
- Operation counting
- Fine-tuning compute
- 1.4 × 10²³ FLOP
1.98288e+24 FLOP [base model compute] + 1.410048e+23 FLOP [addtional vision-language finetune compute] = 2.1238848e+24 FLOP
Assuming same amount of activated parameters (45.9 * 10^9) as for the base model: 6 FLOP / parameter / token * 45.9 * 10^9 activated parameters * 512 * 10^9 tokens = 1.410048e+23 FLOP
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 (restricted use)
- Training code
- Unreleased
- Hugging Face
- MiniMaxAI
https://huggingface.co/MiniMaxAI/MiniMax-VL-01 "MiniMax may terminate this Agreement if you are in breach of any term or condition of this Agreement." code seems to be just inference code: https://github.com/MiniMax-AI/MiniMax-01
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Likely above 10²³ FLOP
- Yes
- Record confidence
- Likely
Sources
Where this record came from and when it was last checked.
- Reference
- MiniMax-01: Scaling Foundation Models with Lightning Attention
- Last updated
- 28 November 2025
The extremes
The ten fastest GPUs that run MiniMax-VL-01
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-VL-01
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
The hardware side
Minimum card
Radeon Instinct MI325X
Memory needed
225.5 GB
Fastest
95.2 tok/s
MiniMax-VL-01 reaches a parameter count of 456.3B. 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: 4.
At the low end it is handled by Radeon Instinct MI325X, with a memory capacity of 256 GB, running it at a compression of IQ4_XS and producing around 59.3 tokens per second.
Top of the range is B300, generating roughly 95.2 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.
Background
MiniMax-VL-01 was published by MiniMax, in the country recorded as China, during January 2025. It comes out of an organisation categorised as industry.
It works in the domain of Vision, Language, Multimodal, and is recorded as performing the task of visual question answering, Language modeling/generation, Question answering.
Its starting point was an existing base model, MiniMax-Text-01. Most models at this scale are adapted from an existing base rather than built from nothing.
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 MiniMaxAI.
Reading the throughput figures
The median result is around 76.1 tokens per second. Exceeding reading speed outright: 4 of them.
Mixture-of-experts routing is why the speeds here look high for the parameter count. Only a fraction is read per token, but the whole thing has to be loaded.
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
Training it took a computation budget of roughly 2.1 × 10²⁴ FLOP, on hardware recorded as NVIDIA H800 SXM5. That figure measures what producing the model cost, and has no bearing on how fast it answers.
Step by step
How to choose a GPU for MiniMax-VL-01
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
Start from what it actually needs, which is the requirement of MiniMax-VL-01, needing around 225.5 GB at a compression of IQ4_XS. 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 a card that seemed fine stops fitting MiniMax-VL-01.
-
03
Set a quality floor
The quantisation column varies by card, because a bigger card holds a more accurate copy, reaching a compression of IQ4_XS 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-VL-01. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B300, at 95.2 tok/s.
-
05
Read the fit column last
The fit column separates cards that just manage it from those with room to spare, in the case of MiniMax-VL-01. 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 MiniMax-VL-01.
Answers
MiniMax-VL-01 — common questions
MiniMax-VL-01— 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-VL-01— how much compute was used to train it?
Training consumed around 2.1 × 10²⁴ FLOP, on hardware recorded as 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.
MiniMax-VL-01— 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 79.3 GB. Every figure here assumes the whole model is resident on the card.
MiniMax-VL-01— would two GPUs run it faster?
Capacity adds across cards; throughput does not. The number of cards already holding it on their own: 4. So a second card is rarely the answer here.
MiniMax-VL-01— 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: 2. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.
MiniMax-VL-01— 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: 57–152 tok/s on B300. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.
MiniMax-VL-01— what GPU do I need to run it?
The smallest card in our catalogue that holds it is Radeon Instinct MI325X, with a memory capacity of 256 GB. It runs the model at a compression of IQ4_XS using about 225.5 GB, and produces roughly 59.3 tokens per second. The number of cards able to run it in total: 4.
MiniMax-VL-01— how fast is it on a GPU?
It depends on the card. The quickest we calculate is B300, at about 95.2 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: 4.
MiniMax-VL-01— how much VRAM does it need?
It needs about 225.5 GB at a compression of IQ4_XS, 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-VL-01— 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-VL-01— how many parameters does it have?
It has a parameter count of 456.3B. 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-VL-01— who created it?
It was published by MiniMax, based in China, an organisation categorised as industry.
MiniMax-VL-01— when was it released?
It was published in January 2025.
MiniMax-VL-01— what is it used for?
It works in the domain of Vision, Language, Multimodal, and is recorded as handling the task of visual question answering, Language modeling/generation, Question answering. These are the areas it was designed around; they describe intent rather than a hard boundary.
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.