Me Llama 70B TPS calculator

Open weights Yale School of Medicine,University of Florida,University of Texas Health Science Center 70B parameters February 2024

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

61 cards that can run it

818 cards we hold specifications for

Smallest card that fits

A100 PCIe 40 GB

40 GB · IQ4_XS · 23.2 tok/s

Fastest card

B200

48.4 tok/s · 180 GB

Which GPUs can run Me Llama 70B?

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.

61 cards match

Calculating
Needs Quantisation Fit
48.4 tok/s

41–58

B200 NVIDIA 180 GB 8,000 GB/s Jan 2024 72.5 GB Q8_0 Comfortable
48.4 tok/s

41–58

B300 NVIDIA 288 GB 8,000 GB/s Sep 2025 72.5 GB Q8_0 Comfortable
38.7 tok/s

23–62 · low confidence

Radeon Instinct MI350X AMD 288 GB 8,190 GB/s Jan 2025 72.5 GB Q8_0 Comfortable
38.7 tok/s

23–62 · low confidence

Radeon Instinct MI355X AMD 288 GB 8,190 GB/s Jan 2025 72.5 GB Q8_0 Comfortable
30.9 tok/s

19–49 · low confidence

Radeon Instinct MI300 AMD 128 GB 6,550 GB/s Jan 2023 72.5 GB Q8_0 Comfortable
29.6 tok/s

25–36

H200 NVL NVIDIA 141 GB 4,890 GB/s Nov 2024 72.5 GB Q8_0 Comfortable
29.6 tok/s

25–36

H200 SXM 141 GB NVIDIA 141 GB 4,890 GB/s Nov 2024 72.5 GB Q8_0 Comfortable
29.5 tok/s

25–35

H100 SXM5 80 GB NVIDIA 80 GB 3,360 GB/s Oct 2022 56.2 GB Q6_K Comfortable
29.5 tok/s

25–35

H800 SXM5 NVIDIA 80 GB 3,360 GB/s Mar 2023 56.2 GB Q6_K Comfortable
28.3 tok/s

17–45 · low confidence

Radeon Instinct MI325X AMD 256 GB 6,000 GB/s Oct 2024 72.5 GB Q8_0 Comfortable
26.1 tok/s

22–31

GRID A100B NVIDIA 48 GB 1,870 GB/s May 2020 39.9 GB Q4_K_M Tight
25.1 tok/s

15–40 · low confidence

Radeon Instinct MI300A AMD 128 GB 5,325 GB/s Dec 2023 72.5 GB Q8_0 Comfortable
25.1 tok/s

15–40 · low confidence

Radeon Instinct MI300X AMD 192 GB 5,325 GB/s Dec 2023 72.5 GB Q8_0 Comfortable
25.1 tok/s

15–40 · low confidence

Radeon Instinct MI308X AMD 192 GB 5,325 GB/s Dec 2023 72.5 GB Q8_0 Comfortable
23.8 tok/s

20–29

H100 NVL 94 GB NVIDIA 94 GB 3,940 GB/s Mar 2023 72.5 GB Q8_0 Tight
23.2 tok/s

20–28

A100 PCIe 40 GB NVIDIA 40 GB 1,560 GB/s Jun 2020 35.8 GB IQ4_XS Tight
23.2 tok/s

20–28

A100 SXM4 40 GB NVIDIA 40 GB 1,560 GB/s May 2020 35.8 GB IQ4_XS Tight
23.2 tok/s

20–28

A800 PCIe 40 GB NVIDIA 40 GB 1,560 GB/s Nov 2022 35.8 GB IQ4_XS Tight
20.3 tok/s

17–24

H100 PCIe 96 GB NVIDIA 96 GB 3,360 GB/s Mar 2023 72.5 GB Q8_0 Tight
20.3 tok/s

17–24

H100 SXM5 94 GB NVIDIA 94 GB 3,360 GB/s Mar 2023 72.5 GB Q8_0 Tight
20.3 tok/s

17–24

H100 SXM5 96 GB NVIDIA 96 GB 3,360 GB/s Mar 2023 72.5 GB Q8_0 Tight
18.7 tok/s

16–22

RTX PRO 5000 Blackwell NVIDIA 48 GB 1,340 GB/s Mar 2025 39.9 GB Q4_K_M Tight
17.9 tok/s

15–22

A100 SXM4 80 GB NVIDIA 80 GB 2,040 GB/s Nov 2020 56.2 GB Q6_K Comfortable
17.9 tok/s

15–22

A100X NVIDIA 80 GB 2,040 GB/s Jun 2021 56.2 GB Q6_K Comfortable
17.9 tok/s

15–22

A800 SXM4 80 GB NVIDIA 80 GB 2,040 GB/s Aug 2022 56.2 GB Q6_K 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
Yale School of Medicine,University of Florida,University of Texas Health Science Center
Organisation type
Academia,Academia,Academia
Country
United States of America
Published
20 February 2024
Authors
Qianqian Xie, Qingyu Chen, Aokun Chen, Cheng Peng, Yan Hu, Fongci Lin, Xueqing Peng, Jimin Huang, Jeffrey Zhang, Vipina Keloth, Xinyu Zhou, Lingfei Qian, Huan He, Dennis Shung, Lucila Ohno-Machado, Yonghui Wu, Hua Xu, Jiang Bian

What it does

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

Domain
Language, Medicine
Task
Language modeling/generation, Question answering, Medical diagnosis, Named entity recognition (NER), Text classification, Text summarization
Base model
Llama 2-70B
Numerical format
BF16

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
70B

70B

Training data
129,000,000,000 tokens

"129B pre-training tokens and 214K instruction tuning samples from diverse biomedical and clinical data sources"

Epochs
1

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.

How it was established
Operation counting,Hardware
Fine-tuning compute
4.3 × 10²² FLOP

6 FLOP / parameter / token * 70 * 10^9 parameters * 129 * 10^9 pre-training tokens [instruction-tuning is negligible] = 5.418e+22 FLOP 312000000000000 FLOP / GPU / sec [A100, bf16] * 100000 GPU-hours * 3600 sec/ hour * 0.3 [assumed utilization] = 3.3696e+22 FLOP sqrt(3.3696e+22 * 5.418e+22) = 4.2727617e+22 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 A100 SXM4 80 GB
Chip-hours
100,000

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
Unreleased

MIT license + llama 2 restirctions + PhysioNet Credentialed Health DUA 1.5.0 https://github.com/BIDS-Xu-Lab/Me-LLaMA

How it is classified

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

Record confidence
Confident

Sources

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

Reference
Me LLaMA: Foundation Large Language Models for Medical Applications
Last updated
28 November 2025

The extremes

The ten fastest GPUs that run Me Llama 70B

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 48.4 tok/s
  2. 02 B200 180 GB · 8,000 GB/s · Q8_0 48.4 tok/s
  3. 03 Radeon Instinct MI350X 288 GB · 8,190 GB/s · Q8_0 38.7 tok/s
  4. 04 Radeon Instinct MI355X 288 GB · 8,190 GB/s · Q8_0 38.7 tok/s
  5. 05 Radeon Instinct MI300 128 GB · 6,550 GB/s · Q8_0 30.9 tok/s
  6. 06 H200 NVL 141 GB · 4,890 GB/s · Q8_0 29.6 tok/s
  7. 07 H200 SXM 141 GB 141 GB · 4,890 GB/s · Q8_0 29.6 tok/s
  8. 08 H800 SXM5 80 GB · 3,360 GB/s · Q6_K 29.5 tok/s
  9. 09 H100 SXM5 80 GB 80 GB · 3,360 GB/s · Q6_K 29.5 tok/s
  10. 10 Radeon Instinct MI325X 256 GB · 6,000 GB/s · Q8_0 28.3 tok/s

The smallest GPUs that still run Me Llama 70B

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

  1. 01 A800 PCIe 40 GB 40 GB · needs 35.8 GB · IQ4_XS · tight 23.2 tok/s
  2. 02 A100 PCIe 40 GB 40 GB · needs 35.8 GB · IQ4_XS · tight 23.2 tok/s
  3. 03 A100 SXM4 40 GB 40 GB · needs 35.8 GB · IQ4_XS · tight 23.2 tok/s
  4. 04 Radeon PRO W7900D 48 GB · needs 39.9 GB · Q4_K_M · tight 9.4 tok/s
  5. 05 RTX PRO 5000 Blackwell 48 GB · needs 39.9 GB · Q4_K_M · tight 18.7 tok/s
  6. 06 RTX 5880 Ada Generation 48 GB · needs 39.9 GB · Q4_K_M · tight 12.1 tok/s
  7. 07 L20 48 GB · needs 39.9 GB · Q4_K_M · tight 12.1 tok/s
  8. 08 Radeon PRO W7800 48 GB 48 GB · needs 39.9 GB · Q4_K_M · tight 9.4 tok/s
  9. 09 Radeon PRO W7900 48 GB · needs 39.9 GB · Q4_K_M · tight 9.4 tok/s
  10. 10 Data Center GPU Max 1100 48 GB · needs 39.9 GB · Q4_K_M · tight 11.2 tok/s

What the numbers mean

Hardware requirements in practice

Minimum card

A100 PCIe 40 GB

Memory needed

35.8 GB

Fastest

48.4 tok/s

Me Llama 70B sits at 70B parameters, which puts it above consumer hardware and into the range where a card is bought for this purpose rather than repurposed for it. 61 of the cards we track can hold it.

The entry point is the A100 PCIe 40 GB: 40 GB of memory, IQ4_XS compression, roughly 23.2 tokens per second.

Top of the range is the B200, at roughly 48.4 tokens per second thanks to 8,000 GB/s of bandwidth.

About this model

Me Llama 70B was published by Yale School of Medicine,University of Florida,University of Texas Health Science Center, in United States of America, in February 2024. academia,Academia,Academia is the category the publisher falls under.

It works in Language, Medicine, and is recorded as doing language modeling/generation, Question answering, Medical diagnosis, Named entity recognition (NER), Text classification, Text summarization.

It builds on Llama 2-70B, which is why it shares that model's general shape and size.

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.

How fast it runs, and why

The median result is around 17.1 tokens per second; 49 cards produce text faster than most people read it.

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

Because the architecture is recorded, the memory column is derived rather than estimated.

What went into building it

Around 129,000,000,000 tokens went into training it.

Step by step

How to choose a GPU for Me Llama 70B

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

  1. 01

    Check what it needs before anything else

    Every card here has been checked against Me Llama 70B — around 35.8 GB at IQ4_XS. Capacity is the gate — a card either holds it or it does not.

  2. 02

    Set the context length you will work at

    The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context Me Llama 70B can slip off a card that handles short questions easily.

  3. 03

    Choose how far you will compress it

    The quantisation column varies by card, because a bigger card holds a more accurate copy of Me Llama 70B — IQ4_XS on the smallest card that fits. Set a floor to hold the comparison at one level.

  4. 04

    Rank by throughput rather than spec sheet

    Ranking by tokens per second for Me Llama 70B follows memory bandwidth, not core counts, which is why the B200 tops it at 48.4 tok/s.

  5. 05

    Check the fit verdict before buying

    The fit column separates cards that just manage Me Llama 70B from those with room to spare. Buy for the second if the context might grow.

  6. 06

    See what else that card runs

    Every card name links to its own page, which runs the same calculation across the whole model catalogue. Worth a look before buying for Me Llama 70B alone — a card is usually bought for more than one model.

Answers

Me Llama 70B — common questions

01

How fast is Me Llama 70B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 48.4 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 49 of the cards that can run Me Llama 70B clear that.

02

How much VRAM does Me Llama 70B need?

About 35.8 GB at IQ4_XS 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.

03

Is Me Llama 70B open source?

Its weights are published, so Me Llama 70B 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.

04

How many parameters does Me Llama 70B have?

Me Llama 70B has 70B parameters. 70B. 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.

05

Who created Me Llama 70B?

Me Llama 70B was published by Yale School of Medicine,University of Florida,University of Texas Health Science Center, based in United States of America, categorised as academia,Academia,Academia.

06

When was Me Llama 70B released?

Me Llama 70B was published in February 2024. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

07

What is Me Llama 70B used for?

Me Llama 70B works in Language, Medicine, and is recorded as handling language modeling/generation, Question answering, Medical diagnosis, Named entity recognition (NER), Text classification, Text summarization. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

08

Where can I download Me Llama 70B?

The weights for Me Llama 70B are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

09

Can I run Me Llama 70B if it does not fit in my GPU?

Only by offloading, which is usually a false economy: the part in system memory drags the whole thing down — the nearest miss we calculate is short by 11.1 GB. Our figures for Me Llama 70B assume it is fully resident.

10

Would two GPUs run Me Llama 70B faster?

A second card roughly doubles the memory available but not the generation rate. With 61 cards already able to run Me Llama 70B alone, the case for pairing is weak.

11

Why does the quantisation differ between cards for Me Llama 70B?

A larger card holds a more accurate copy. Across the cards that run Me Llama 70B, 4 compression levels are used; the floor control above pins it to one.

12

How accurate are these Me Llama 70B speed estimates?

These are estimates with real error bars. The fastest result here, 41–58 tok/s on the B200, could reasonably land anywhere in its published range depending on which runtime you use.

13

What GPU do I need to run Me Llama 70B?

The smallest card in our catalogue that holds Me Llama 70B is the A100 PCIe 40 GB, with 40 GB of memory. It runs the model at IQ4_XS using about 35.8 GB, and produces roughly 23.2 tokens per second. 61 cards in total can run it.

Source

Original publication

Record last updated 28 November 2025

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