MetaMath 70B 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
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 MetaMath 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
- University of Cambridge,Southern University of Science and Technology (SUSTech),Hong Kong University of Science and Technology (HKUST),Huawei Noah's Ark Lab,Alan Turing Institute,Max Planck Institute for Intelligent Systems
- Organisation type
- Academia,Academia,Academia,Industry,Government,Academia
- Country
- United Kingdom of Great Britain and Northern Ireland, China, Hong Kong, Germany
- Published
- 3 May 2024
- Authors
- Longhui Yu, Weisen Jiang, Han Shi, Jincheng Yu, Zhengying Liu, Yu Zhang, James T. Kwok, Zhenguo Li, Adrian Weller, Weiyang Liu
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
- Task
- Quantitative reasoning
- 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
- Training data
- tokens
- Epochs
- 3
70B
160K examples 396 MB 396 MB * 200000 english words per MB * 4/3 tokens per english word = 105600000 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.
- How it was established
- Operation counting
- Fine-tuning compute
- 1.3 × 10²⁰ FLOP
Likely confidence because I am not sure about the epochs 6*70*10^9*105600000*3 = 1.33056 × 10^20
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)
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Likely
Sources
Where this record came from and when it was last checked.
- Reference
- MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models
- Last updated
- 28 November 2025
The extremes
The ten fastest GPUs that run MetaMath 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.
- 01 B300 288 GB · 8,000 GB/s · Q8_0 48.4 tok/s
- 02 B200 180 GB · 8,000 GB/s · Q8_0 48.4 tok/s
- 03 Radeon Instinct MI350X 288 GB · 8,190 GB/s · Q8_0 38.7 tok/s
- 04 Radeon Instinct MI355X 288 GB · 8,190 GB/s · Q8_0 38.7 tok/s
- 05 Radeon Instinct MI300 128 GB · 6,550 GB/s · Q8_0 30.9 tok/s
- 06 H200 NVL 141 GB · 4,890 GB/s · Q8_0 29.6 tok/s
- 07 H200 SXM 141 GB 141 GB · 4,890 GB/s · Q8_0 29.6 tok/s
- 08 H800 SXM5 80 GB · 3,360 GB/s · Q6_K 29.5 tok/s
- 09 H100 SXM5 80 GB 80 GB · 3,360 GB/s · Q6_K 29.5 tok/s
- 10 Radeon Instinct MI325X 256 GB · 6,000 GB/s · Q8_0 28.3 tok/s
The smallest GPUs that still run MetaMath 70B
The cheapest route in, by memory capacity. A tight fit runs the model but leaves nothing spare for a longer conversation.
- 01 A800 PCIe 40 GB 40 GB · needs 34.9 GB · Q3_K_M · tight 25.5 tok/s
- 02 A100 PCIe 40 GB 40 GB · needs 34.9 GB · Q3_K_M · tight 25.5 tok/s
- 03 A100 SXM4 40 GB 40 GB · needs 34.9 GB · Q3_K_M · tight 25.5 tok/s
- 04 Radeon PRO W7900D 48 GB · needs 43.0 GB · Q4_K_M · tight 9.4 tok/s
- 05 RTX PRO 5000 Blackwell 48 GB · needs 43.0 GB · Q4_K_M · tight 18.7 tok/s
- 06 RTX 5880 Ada Generation 48 GB · needs 43.0 GB · Q4_K_M · tight 12.1 tok/s
- 07 L20 48 GB · needs 43.0 GB · Q4_K_M · tight 12.1 tok/s
- 08 Radeon PRO W7800 48 GB 48 GB · needs 43.0 GB · Q4_K_M · tight 9.4 tok/s
- 09 Radeon PRO W7900 48 GB · needs 43.0 GB · Q4_K_M · tight 9.4 tok/s
- 10 Data Center GPU Max 1100 48 GB · needs 43.0 GB · Q4_K_M · tight 11.2 tok/s
What the numbers mean
What it takes to run this model
Minimum card
A100 PCIe 40 GB
Memory needed
34.9 GB
Fastest
48.4 tok/s
MetaMath 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 smallest card that holds it is the A100 PCIe 40 GB with 40 GB, running it at Q3_K_M and producing around 25.5 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.
Where it came from
MetaMath 70B was published by University of Cambridge,Southern University of Science and Technology (SUSTech),Hong Kong University of Science and Technology (HKUST),Huawei Noah's Ark Lab,Alan Turing Institute,Max Planck Institute for Intelligent Systems, in United Kingdom of Great Britain and Northern Ireland, in May 2024. It comes out of academia,Academia,Academia,Industry,Government,Academia.
It works in Language, and is recorded as doing quantitative reasoning.
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.
Understanding the speeds
Half the cards that hold it manage more than 17.1 tokens per second, and 50 exceed reading speed outright.
It is a dense model, so every parameter is read for every token produced. That makes speed track memory bandwidth almost exactly — a card with twice the bandwidth generates roughly twice as fast.
Memory here is estimated from size rather than computed from the architecture, which is not recorded for this model — the numbers are indicative rather than exact.
Step by step
How to choose a GPU for MetaMath 70B
The table above has already assessed every card we hold specifications for against this model. Getting to your answer takes six steps.
-
01
Read the memory figure first
Every card here has been checked against MetaMath 70B — around 34.9 GB at Q3_K_M. Capacity is the gate — a card either holds it or it does not.
-
02
Set the context length you will work at
Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for MetaMath 70B.
-
03
Set a quality floor
The quantisation column varies by card, because a bigger card holds a more accurate copy of MetaMath 70B — Q3_K_M on the smallest card that fits. Set a floor to hold the comparison at one level.
-
04
Rank by throughput rather than spec sheet
The speed ordering for MetaMath 70B is effectively an ordering by memory bandwidth, which is why the B200 tops it at 48.4 tok/s.
-
05
Look at the headroom, not just the fit
A tight fit runs MetaMath 70B but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.
-
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 MetaMath 70B alone — a card is usually bought for more than one model.
Answers
MetaMath 70B — common questions
Would two GPUs run MetaMath 70B faster?
A second card roughly doubles the memory available but not the generation rate. With 61 cards already able to run MetaMath 70B alone, the case for pairing is weak.
Why does the quantisation differ between cards for MetaMath 70B?
A larger card holds a more accurate copy. Across the cards that run MetaMath 70B, 5 compression levels are used; the floor control above pins it to one.
How accurate are these MetaMath 70B speed estimates?
They are calculated from specifications rather than measured, and each carries a range — 29–77 tok/s on the B200, for instance. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.
What GPU do I need to run MetaMath 70B?
The smallest card in our catalogue that holds MetaMath 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.
How fast is MetaMath 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 MetaMath 70B clear that.
How much VRAM does MetaMath 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.
Is MetaMath 70B open source?
Its weights are published, so MetaMath 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.
How many parameters does MetaMath 70B have?
MetaMath 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.
Who created MetaMath 70B?
MetaMath 70B was published by University of Cambridge,Southern University of Science and Technology (SUSTech),Hong Kong University of Science and Technology (HKUST),Huawei Noah's Ark Lab,Alan Turing Institute,Max Planck Institute for Intelligent Systems, based in United Kingdom of Great Britain and Northern Ireland, categorised as academia,Academia,Academia,Industry,Government,Academia.
When was MetaMath 70B released?
MetaMath 70B was published in May 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.
What is MetaMath 70B used for?
MetaMath 70B works in Language, and is recorded as handling quantitative reasoning. 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.
Where can I download MetaMath 70B?
The weights for MetaMath 70B are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.
Can I run MetaMath 70B if it does not fit in my GPU?
It can be split between the card and system memory, but MetaMath 70B generates painfully slowly that way — the nearest miss we calculate is short by 14.2 GB. Nothing on this page assumes offloading.
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.