TigerBot-70B TPS calculator

Open weights Tigerobo 70B parameters September 2023

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 · Q3_K_M · 25.5 tok/s

Fastest card

B200

48.4 tok/s · 180 GB

Which GPUs can run TigerBot-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

29–77 · low confidence

B200 NVIDIA 180 GB 8,000 GB/s Jan 2024 75.6 GB Q8_0 Comfortable
48.4 tok/s

29–77 · low confidence

B300 NVIDIA 288 GB 8,000 GB/s Sep 2025 75.6 GB Q8_0 Comfortable
38.7 tok/s

23–62 · low confidence

Radeon Instinct MI350X AMD 288 GB 8,190 GB/s Jan 2025 75.6 GB Q8_0 Comfortable
38.7 tok/s

23–62 · low confidence

Radeon Instinct MI355X AMD 288 GB 8,190 GB/s Jan 2025 75.6 GB Q8_0 Comfortable
30.9 tok/s

19–49 · low confidence

Radeon Instinct MI300 AMD 128 GB 6,550 GB/s Jan 2023 75.6 GB Q8_0 Comfortable
29.6 tok/s

18–47 · low confidence

H200 NVL NVIDIA 141 GB 4,890 GB/s Nov 2024 75.6 GB Q8_0 Comfortable
29.6 tok/s

18–47 · low confidence

H200 SXM 141 GB NVIDIA 141 GB 4,890 GB/s Nov 2024 75.6 GB Q8_0 Comfortable
29.5 tok/s

18–47 · low confidence

H100 SXM5 80 GB NVIDIA 80 GB 3,360 GB/s Oct 2022 59.3 GB Q6_K Comfortable
29.5 tok/s

18–47 · low confidence

H800 SXM5 NVIDIA 80 GB 3,360 GB/s Mar 2023 59.3 GB Q6_K Comfortable
28.3 tok/s

17–45 · low confidence

Radeon Instinct MI325X AMD 256 GB 6,000 GB/s Oct 2024 75.6 GB Q8_0 Comfortable
26.1 tok/s

16–42 · low confidence

GRID A100B NVIDIA 48 GB 1,870 GB/s May 2020 43.0 GB Q4_K_M Tight
25.5 tok/s

15–41 · low confidence

A100 PCIe 40 GB NVIDIA 40 GB 1,560 GB/s Jun 2020 34.9 GB Q3_K_M Tight
25.5 tok/s

15–41 · low confidence

A100 SXM4 40 GB NVIDIA 40 GB 1,560 GB/s May 2020 34.9 GB Q3_K_M Tight
25.5 tok/s

15–41 · low confidence

A800 PCIe 40 GB NVIDIA 40 GB 1,560 GB/s Nov 2022 34.9 GB Q3_K_M Tight
25.1 tok/s

15–40 · low confidence

Radeon Instinct MI300A AMD 128 GB 5,325 GB/s Dec 2023 75.6 GB Q8_0 Comfortable
25.1 tok/s

15–40 · low confidence

Radeon Instinct MI300X AMD 192 GB 5,325 GB/s Dec 2023 75.6 GB Q8_0 Comfortable
25.1 tok/s

15–40 · low confidence

Radeon Instinct MI308X AMD 192 GB 5,325 GB/s Dec 2023 75.6 GB Q8_0 Comfortable
23.8 tok/s

14–38 · low confidence

H100 NVL 94 GB NVIDIA 94 GB 3,940 GB/s Mar 2023 75.6 GB Q8_0 Tight
21.8 tok/s

13–35 · low confidence

H100 SXM5 64 GB NVIDIA 64 GB 2,020 GB/s Mar 2023 51.2 GB Q5_K_M Tight
20.3 tok/s

12–33 · low confidence

H100 PCIe 96 GB NVIDIA 96 GB 3,360 GB/s Mar 2023 75.6 GB Q8_0 Tight
20.3 tok/s

12–33 · low confidence

H100 SXM5 94 GB NVIDIA 94 GB 3,360 GB/s Mar 2023 75.6 GB Q8_0 Tight
20.3 tok/s

12–33 · low confidence

H100 SXM5 96 GB NVIDIA 96 GB 3,360 GB/s Mar 2023 75.6 GB Q8_0 Tight
18.7 tok/s

11–30 · low confidence

RTX PRO 5000 Blackwell NVIDIA 48 GB 1,340 GB/s Mar 2025 43.0 GB Q4_K_M Tight
17.9 tok/s

11–29 · low confidence

A100 SXM4 80 GB NVIDIA 80 GB 2,040 GB/s Nov 2020 59.3 GB Q6_K Comfortable
17.9 tok/s

11–29 · low confidence

A100X NVIDIA 80 GB 2,040 GB/s Jun 2021 59.3 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
Tigerobo
Organisation type
Industry
Country
China
Published
6 September 2023
Authors
Ye Chen, Wei Cai, Liangmin Wu, Xiaowei Li, Zhanxuan Xin, Cong Fu

What it does

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

Domain
Language
Task
Chat, Language generation, Language modeling/generation, Question answering
Base model
Llama 2-70B

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
300,000,000,000 tokens
Batch size
4,000,000

from paper: "We pretrained TigerBot models using a global batch size (GBS) of 4M tokens, while fine-tuned models with a GBS as small as 100–400k tokens" It's also based on pretrained Llama 2, which also used a batch size of 4M

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
1 × 10²⁴ FLOP

~1.02e24 Tigerobo did ~2.1e23 additional pre-training. We estimated Llama 2 was trained on 8.1e23 FLOP.

How it was established
Operation counting
Fine-tuning compute
1.3 × 10²³ FLOP

70b * 300b * 6 = 126000*10^18 = 1.26*10^23

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
Chips used
512
Power draw
406.9 kW
Data centre
Paper on TigerBot-70B

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
Open source

Apache 2.0 https://github.com/TigerResearch/TigerBot/blob/main/README_en.md but it's also a Llama 2 finetune. training code here: https://github.com/TigerResearch/TigerBot/tree/main/train They released a 5% sample of training data: " On this basis, we randomly sampled 100G of data and released it open source."

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
Confident

Sources

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

Reference
TigerBot: An Open Multilingual Multitask LLM
Last updated
28 November 2025

The extremes

What the numbers mean

The hardware side

Minimum card

A100 PCIe 40 GB

Memory needed

34.9 GB

Fastest

48.4 tok/s

TigerBot-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.

At the low end, a A100 PCIe 40 GB handles it — 40 GB, at Q3_K_M, for about 25.5 tokens per second.

At the other end, a B200 generates roughly 48.4 tokens per second on it, on the strength of 8,000 GB/s of memory bandwidth.

Where it came from

TigerBot-70B was published by Tigerobo, in China, in September 2023. The organisation is categorised as industry.

It works in Language, and is recorded as doing chat, Language generation, Language modeling/generation, Question answering.

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

Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded.

Understanding the speeds

Across every card that can run it, the middle of the range is about 17.1 tokens per second, and 50 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.

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.

Training and provenance

Producing it required around 1 × 10²⁴ FLOP of arithmetic, on NVIDIA A100, which is a statement about the training budget rather than about inference.

The training set ran to roughly 300,000,000,000 tokens.

Step by step

How to choose a GPU for TigerBot-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

    Read the memory figure first

    The table lists every card that can hold TigerBot-70B — around 34.9 GB at Q3_K_M. That figure, not the card's headline performance, is what decides whether it runs.

  2. 02

    Decide how long your conversations run

    Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for TigerBot-70B.

  3. 03

    Set a quality floor

    Each card runs the least-compressed copy it can hold — Q3_K_M on the smallest card that fits. Setting a floor drops the cards that only manage TigerBot-70B by squeezing it further than you would want.

  4. 04

    Rank by throughput rather than spec sheet

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

  5. 05

    Read the fit column last

    The fit column separates cards that just manage TigerBot-70B 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 TigerBot-70B alone — a card is usually bought for more than one model.

Answers

TigerBot-70B — common questions

01

Who created TigerBot-70B?

TigerBot-70B was published by Tigerobo, based in China, categorised as industry.

02

When was TigerBot-70B released?

TigerBot-70B was published in September 2023. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

03

What is TigerBot-70B used for?

TigerBot-70B works in Language, and is recorded as handling chat, Language generation, Language modeling/generation, Question answering. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

04

Where can I download TigerBot-70B?

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

05

How much compute was used to train TigerBot-70B?

Around 1 × 10²⁴ FLOP, on NVIDIA A100. 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.

06

Can I run TigerBot-70B 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 TigerBot-70B is rarely worth using — the nearest miss we calculate is short by 14.2 GB. Every figure here assumes the whole model is on the card.

07

Would two GPUs run TigerBot-70B faster?

Capacity adds across cards; throughput does not. Since 61 of the cards we track already hold TigerBot-70B on their own, a second card is rarely the answer here.

08

Why does the quantisation differ between cards for TigerBot-70B?

Because capacity varies, so does how hard TigerBot-70B has to be squeezed — 5 distinct levels appear in the table above. Set a minimum quality to compare at one.

09

How accurate are these TigerBot-70B speed estimates?

These are estimates with real error bars. The fastest result here, 29–77 tok/s on the B200, could reasonably land anywhere in its published range depending on which runtime you use.

10

What GPU do I need to run TigerBot-70B?

The smallest card in our catalogue that holds TigerBot-70B is the A100 PCIe 40 GB, with 40 GB of memory. It runs the model at Q3_K_M using about 34.9 GB, and produces roughly 25.5 tokens per second. 61 cards in total can run it.

11

How fast is TigerBot-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 50 of the cards that can run TigerBot-70B clear that.

12

How much VRAM does TigerBot-70B need?

About 34.9 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.

13

Is TigerBot-70B open source?

Its weights are published, so TigerBot-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.

14

How many parameters does TigerBot-70B have?

TigerBot-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.

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.