ProxylessNAS
No estimate
No hardware requirements for this model
This model's weights are open, but no parameter count has been published for it. Every memory and speed figure starts from that number, so we would rather show nothing than a fabricated estimate.
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
- Massachusetts Institute of Technology (MIT)
- Organisation type
- Academia
- Country
- United States of America
- Published
- 23 February 2019
- Authors
- Han Cai, Ligeng Zhu, and Song Han
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Vision
- Task
- Image classification, Neural Architecture Search - NAS
- Numerical format
- FP32
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.
- Training data
- 1,230,000 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
- 3.7 × 10¹⁸ FLOP
- How it was established
- Hardware
For their searched Imagenet models, they used 200 GPU hours on a V100 GPU. At FP32, a V100 GPU has a peak performance of 1.56E+13 FLOPS. Utilization rate of 0.33. 200 h * 3600 second / hour* 1.6e+13 flop /second * 0.33 = 3.7e+18 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 V100
- Chip-hours
- 200
- Compute cost
- $123
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
- Open source
MIT for code+weights https://github.com/MIT-HAN-LAB/ProxylessNAS
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Confident
- Citations
- 2,054
Sources
Where this record came from and when it was last checked.
- Reference
- ProxylessNAS: Direct neural architecture search on target task and hardware
- Last updated
- 25 May 2026
What the numbers mean
Where it came from
ProxylessNAS was published by Massachusetts Institute of Technology (MIT), in the country recorded as United States of America, during February 2019. The category the publisher falls under is academia.
It works in the domain of Vision, and is recorded as performing the task of image classification, Neural Architecture Search - NAS.
The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached.
Training and provenance
The training run consumed about 3.7 × 10¹⁸ FLOP, on hardware recorded as NVIDIA V100. 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 1,230,000 tokens of text.
Answers
ProxylessNAS — common questions
ProxylessNAS— what GPU do I need to run it?
We cannot say. It has open weights, but no parameter count has been published for it, and every memory and speed calculation starts from that number. We would rather show nothing than a fabricated estimate.
ProxylessNAS— 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.
ProxylessNAS— how many parameters does it have?
No parameter count has been published for it, which is why no memory or speed figure appears on this page.
ProxylessNAS— who created it?
It was published by Massachusetts Institute of Technology (MIT), based in United States of America, an organisation categorised as academia.
ProxylessNAS— when was it released?
It was published in February 2019. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
ProxylessNAS— what is it used for?
It works in the domain of Vision, and is recorded as handling the task of image classification, Neural Architecture Search - NAS. These are the areas it was designed around; they describe intent rather than a hard boundary.
ProxylessNAS— where can I download it?
The weights are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.
ProxylessNAS— how much compute was used to train it?
Training consumed around 3.7 × 10¹⁸ FLOP, on hardware recorded as NVIDIA V100. 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.
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.