FixRes ResNeXt-101 WSL TPS calculator

Open weights Facebook AI 829M parameters June 2019

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 that can run it

818 cards we hold specifications for

Smallest card that fits

Tesla C1080

4 GB · Q8_0 · 44.5 tok/s

Fastest card

B200

4,087 tok/s · 180 GB

Which GPUs can run FixRes ResNeXt-101 WSL?

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.

818 cards match

Calculating
Needs Quantisation Fit
4,087 tok/s

2,452–6,539 · low confidence

B200 NVIDIA 180 GB 8,000 GB/s Jan 2024 1.6 GB Q8_0 Comfortable
4,087 tok/s

2,452–6,539 · low confidence

B300 NVIDIA 288 GB 8,000 GB/s Sep 2025 1.6 GB Q8_0 Comfortable
3,264 tok/s

1,958–5,222 · low confidence

Radeon Instinct MI350X AMD 288 GB 8,190 GB/s Jan 2025 1.6 GB Q8_0 Comfortable
3,264 tok/s

1,958–5,222 · low confidence

Radeon Instinct MI355X AMD 288 GB 8,190 GB/s Jan 2025 1.6 GB Q8_0 Comfortable
2,610 tok/s

1,566–4,176 · low confidence

Radeon Instinct MI300 AMD 128 GB 6,550 GB/s Jan 2023 1.6 GB Q8_0 Comfortable
2,498 tok/s

1,499–3,997 · low confidence

H200 NVL NVIDIA 141 GB 4,890 GB/s Nov 2024 1.6 GB Q8_0 Comfortable
2,498 tok/s

1,499–3,997 · low confidence

H200 SXM 141 GB NVIDIA 141 GB 4,890 GB/s Nov 2024 1.6 GB Q8_0 Comfortable
2,391 tok/s

1,435–3,826 · low confidence

Radeon Instinct MI325X AMD 256 GB 6,000 GB/s Oct 2024 1.6 GB Q8_0 Comfortable
2,122 tok/s

1,273–3,395 · low confidence

Radeon Instinct MI300A AMD 128 GB 5,325 GB/s Dec 2023 1.6 GB Q8_0 Comfortable
2,122 tok/s

1,273–3,395 · low confidence

Radeon Instinct MI300X AMD 192 GB 5,325 GB/s Dec 2023 1.6 GB Q8_0 Comfortable
2,122 tok/s

1,273–3,395 · low confidence

Radeon Instinct MI308X AMD 192 GB 5,325 GB/s Dec 2023 1.6 GB Q8_0 Comfortable
2,013 tok/s

1,208–3,221 · low confidence

H100 NVL 94 GB NVIDIA 94 GB 3,940 GB/s Mar 2023 1.6 GB Q8_0 Comfortable
1,717 tok/s

1,030–2,747 · low confidence

H100 PCIe 96 GB NVIDIA 96 GB 3,360 GB/s Mar 2023 1.6 GB Q8_0 Comfortable
1,717 tok/s

1,030–2,747 · low confidence

H100 SXM5 80 GB NVIDIA 80 GB 3,360 GB/s Oct 2022 1.6 GB Q8_0 Comfortable
1,717 tok/s

1,030–2,747 · low confidence

H100 SXM5 94 GB NVIDIA 94 GB 3,360 GB/s Mar 2023 1.6 GB Q8_0 Comfortable
1,717 tok/s

1,030–2,747 · low confidence

H100 SXM5 96 GB NVIDIA 96 GB 3,360 GB/s Mar 2023 1.6 GB Q8_0 Comfortable
1,717 tok/s

1,030–2,747 · low confidence

H800 SXM5 NVIDIA 80 GB 3,360 GB/s Mar 2023 1.6 GB Q8_0 Comfortable
1,307 tok/s

784–2,091 · low confidence

Radeon Instinct MI250 AMD 128 GB 3,280 GB/s Nov 2021 1.6 GB Q8_0 Comfortable
1,307 tok/s

784–2,091 · low confidence

Radeon Instinct MI250X AMD 128 GB 3,280 GB/s Nov 2021 1.6 GB Q8_0 Comfortable
1,089 tok/s

654–1,743 · low confidence

Data Center GPU Max 1550 Intel 128 GB 3,280 GB/s Jan 2023 1.6 GB Q8_0 Comfortable
1,066 tok/s

640–1,706 · low confidence

Data Center GPU Max Subsystem Intel 128 GB 3,210 GB/s Jan 2023 1.6 GB Q8_0 Comfortable
1,042 tok/s

625–1,668 · low confidence

A100 SXM4 80 GB NVIDIA 80 GB 2,040 GB/s Nov 2020 1.6 GB Q8_0 Comfortable
1,042 tok/s

625–1,668 · low confidence

A100X NVIDIA 80 GB 2,040 GB/s Jun 2021 1.6 GB Q8_0 Comfortable
1,042 tok/s

625–1,668 · low confidence

A800 SXM4 80 GB NVIDIA 80 GB 2,040 GB/s Aug 2022 1.6 GB Q8_0 Comfortable
1,042 tok/s

625–1,668 · low confidence

H100 CNX NVIDIA 80 GB 2,040 GB/s Mar 2023 1.6 GB Q8_0 Comfortable

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
Facebook AI
Organisation type
Industry
Country
United States of America
Published
14 June 2019
Authors
Hugo Touvron, Andrea Vedaldi, Matthijs Douze, Hervé Jégou

What it does

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

Domain
Vision
Task
Image classification

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
829M
Training data
940,000,000 tokens

"Conversely, when training a ResNeXt-101 32x48d pre-trained in weakly-supervised fashion on 940 million public images at resolution 224x224 and further optimizing for test resolution 320x320, we obtain a test top-1 accuracy of 86.4% (top-5: 98.0%) (single-crop)"

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 (non-commercial)
Training code
Open (non-commercial)

code/weights with non-commercial license: https://github.com/facebookresearch/FixRes?tab=License-1-ov-file#readme

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
SOTA improvement

"To the best of our knowledge our ResNeXt-101 32x48d surpasses all other models available in the literature"

Citations
477

Sources

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

Reference
Fixing the train-test resolution discrepancy
Last updated
25 May 2026

The extremes

The ten fastest GPUs that run FixRes ResNeXt-101 WSL

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.

  1. 01 B300 288 GB · 8,000 GB/s · Q8_0 4,087 tok/s
  2. 02 B200 180 GB · 8,000 GB/s · Q8_0 4,087 tok/s
  3. 03 Radeon Instinct MI350X 288 GB · 8,190 GB/s · Q8_0 3,264 tok/s
  4. 04 Radeon Instinct MI355X 288 GB · 8,190 GB/s · Q8_0 3,264 tok/s
  5. 05 Radeon Instinct MI300 128 GB · 6,550 GB/s · Q8_0 2,610 tok/s
  6. 06 H200 NVL 141 GB · 4,890 GB/s · Q8_0 2,498 tok/s
  7. 07 H200 SXM 141 GB 141 GB · 4,890 GB/s · Q8_0 2,498 tok/s
  8. 08 Radeon Instinct MI325X 256 GB · 6,000 GB/s · Q8_0 2,391 tok/s
  9. 09 Radeon Instinct MI300A 128 GB · 5,325 GB/s · Q8_0 2,122 tok/s
  10. 10 Radeon Instinct MI300X 192 GB · 5,325 GB/s · Q8_0 2,122 tok/s

The smallest GPUs that still run FixRes ResNeXt-101 WSL

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

  1. 01 GeForce RTX 4010 4 GB · needs 1.6 GB · Q8_0 · comfortable 49.1 tok/s
  2. 02 RTX A400 4 GB · needs 1.6 GB · Q8_0 · comfortable 49.1 tok/s
  3. 03 RTX 500 Mobile Ada Generation 4 GB · needs 1.6 GB · Q8_0 · comfortable 65.4 tok/s
  4. 04 GeForce RTX 3050 A Mobile 4 GB · needs 1.6 GB · Q8_0 · comfortable 98.1 tok/s
  5. 05 Jetson Orin Nano 4 GB 4 GB · needs 1.6 GB · Q8_0 · comfortable 17.4 tok/s
  6. 06 Radeon RX 6450M 4 GB · needs 1.6 GB · Q8_0 · comfortable 51.0 tok/s
  7. 07 Radeon RX 6550M 4 GB · needs 1.6 GB · Q8_0 · comfortable 57.4 tok/s
  8. 08 Radeon RX 6550S 4 GB · needs 1.6 GB · Q8_0 · comfortable 51.0 tok/s
  9. 09 Arc A310 4 GB · needs 1.6 GB · Q8_0 · comfortable 41.2 tok/s
  10. 10 Arc Pro A30M 4 GB · needs 1.6 GB · Q8_0 · comfortable 42.5 tok/s

What the numbers mean

The hardware side

Minimum card

Tesla C1080

Memory needed

1.6 GB

Fastest

4,087 tok/s

FixRes ResNeXt-101 WSL is small enough at 829M parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.

At the low end, a Tesla C1080 handles it — 4 GB, at Q8_0, for about 44.5 tokens per second.

Top of the range is the B200, at roughly 4,087 tokens per second thanks to 8,000 GB/s of bandwidth.

What this model is

FixRes ResNeXt-101 WSL was published by Facebook AI, in United States of America, in June 2019. The organisation is categorised as industry.

It works in Vision, and is recorded as doing image classification.

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.

What decides the speed

Across every card that can run it, the middle of the range is about 114.8 tokens per second, and 809 of them clear the ten tokens per second that roughly matches reading speed.

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.

How it was trained

It was trained on about 940,000,000 tokens of text.

The reason it appears in this catalogue at all is sOTA improvement.

Step by step

How to choose a GPU for FixRes ResNeXt-101 WSL

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

  1. 01

    Start from the memory column

    Look at what FixRes ResNeXt-101 WSL actually needs — around 1.6 GB at Q8_0. No amount of processing power compensates for a card that cannot hold it.

  2. 02

    Set the context length you will work at

    Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason FixRes ResNeXt-101 WSL stops fitting a card that seemed fine.

  3. 03

    Decide how much compression you will accept

    Compression is what makes FixRes ResNeXt-101 WSL fit smaller cards, at some cost in accuracy — Q8_0 on the smallest card that fits. A minimum quality removes the ones that go too far.

  4. 04

    Compare tokens per second, not specifications

    The speed ordering for FixRes ResNeXt-101 WSL is effectively an ordering by memory bandwidth, which is why the B200 tops it at 4,087 tok/s.

  5. 05

    Read the fit column last

    The fit column separates cards that just manage FixRes ResNeXt-101 WSL from those with room to spare. Buy for the second if the context might grow.

  6. 06

    Open the card you have settled on

    Every card name links to its own page, which runs the same calculation across the whole model catalogue. Worth a look before buying for FixRes ResNeXt-101 WSL alone — a card is usually bought for more than one model.

Answers

FixRes ResNeXt-101 WSL — common questions

01

Where can I download FixRes ResNeXt-101 WSL?

The weights for FixRes ResNeXt-101 WSL are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

02

Can I run FixRes ResNeXt-101 WSL 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 FixRes ResNeXt-101 WSL is rarely worth using. Every figure here assumes the whole model is on the card.

03

Would two GPUs run FixRes ResNeXt-101 WSL faster?

Capacity adds across cards; throughput does not. Since 818 of the cards we track already hold FixRes ResNeXt-101 WSL on their own, a second card is rarely the answer here.

04

Why does the quantisation differ between cards for FixRes ResNeXt-101 WSL?

Because capacity varies, so does how hard FixRes ResNeXt-101 WSL has to be squeezed — 1 distinct levels appear in the table above. Set a minimum quality to compare at one.

05

How accurate are these FixRes ResNeXt-101 WSL speed estimates?

These are estimates with real error bars. The fastest result here, 2,452–6,539 tok/s on the B200, could reasonably land anywhere in its published range depending on which runtime you use.

06

What GPU do I need to run FixRes ResNeXt-101 WSL?

The smallest card in our catalogue that holds FixRes ResNeXt-101 WSL is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 1.6 GB, and produces roughly 44.5 tokens per second. 818 cards in total can run it.

07

How fast is FixRes ResNeXt-101 WSL on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 4,087 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 809 of the cards that can run FixRes ResNeXt-101 WSL clear that.

08

How much VRAM does FixRes ResNeXt-101 WSL need?

About 1.6 GB at Q8_0 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.

09

Can I run FixRes ResNeXt-101 WSL on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 1.6 GB and generating roughly 761 tokens per second — a comfortable fit.

10

Can I run FixRes ResNeXt-101 WSL on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 1.6 GB and generating roughly 466 tokens per second — a comfortable fit.

11

Can I run FixRes ResNeXt-101 WSL on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 1.6 GB and generating roughly 577 tokens per second — a comfortable fit.

12

Can I run FixRes ResNeXt-101 WSL on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 1.6 GB and generating roughly 685 tokens per second — a comfortable fit.

13

Is FixRes ResNeXt-101 WSL open source?

Its weights are published, so FixRes ResNeXt-101 WSL 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.

14

How many parameters does FixRes ResNeXt-101 WSL have?

FixRes ResNeXt-101 WSL has 829M parameters. 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.

15

Who created FixRes ResNeXt-101 WSL?

FixRes ResNeXt-101 WSL was published by Facebook AI, based in United States of America, categorised as industry.

16

When was FixRes ResNeXt-101 WSL released?

FixRes ResNeXt-101 WSL was published in June 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.

17

What is FixRes ResNeXt-101 WSL used for?

FixRes ResNeXt-101 WSL works in Vision, and is recorded as handling image classification. These are the areas it was designed around; they describe intent rather than a hard boundary.

Source

Original publication

Record last updated 25 May 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