DeepSeek-R1-Distill-Llama-70B TPS calculator

Open weights DeepSeek 70B parameters January 2025

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 DeepSeek-R1-Distill-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 73.8 GB Q8_0 Comfortable
48.4 tok/s

41–58

B300 NVIDIA 288 GB 8,000 GB/s Sep 2025 73.8 GB Q8_0 Comfortable
38.7 tok/s

23–62 · low confidence

Radeon Instinct MI350X AMD 288 GB 8,190 GB/s Jan 2025 73.8 GB Q8_0 Comfortable
38.7 tok/s

23–62 · low confidence

Radeon Instinct MI355X AMD 288 GB 8,190 GB/s Jan 2025 73.8 GB Q8_0 Comfortable
30.9 tok/s

19–49 · low confidence

Radeon Instinct MI300 AMD 128 GB 6,550 GB/s Jan 2023 73.8 GB Q8_0 Comfortable
29.6 tok/s

25–36

H200 NVL NVIDIA 141 GB 4,890 GB/s Nov 2024 73.8 GB Q8_0 Comfortable
29.6 tok/s

25–36

H200 SXM 141 GB NVIDIA 141 GB 4,890 GB/s Nov 2024 73.8 GB Q8_0 Comfortable
29.5 tok/s

25–35

H100 SXM5 80 GB NVIDIA 80 GB 3,360 GB/s Oct 2022 57.5 GB Q6_K Comfortable
29.5 tok/s

25–35

H800 SXM5 NVIDIA 80 GB 3,360 GB/s Mar 2023 57.5 GB Q6_K Comfortable
28.3 tok/s

17–45 · low confidence

Radeon Instinct MI325X AMD 256 GB 6,000 GB/s Oct 2024 73.8 GB Q8_0 Comfortable
26.1 tok/s

22–31

GRID A100B NVIDIA 48 GB 1,870 GB/s May 2020 41.2 GB Q4_K_M Tight
25.5 tok/s

22–31

A100 PCIe 40 GB NVIDIA 40 GB 1,560 GB/s Jun 2020 33.0 GB Q3_K_M Tight
25.5 tok/s

22–31

A100 SXM4 40 GB NVIDIA 40 GB 1,560 GB/s May 2020 33.0 GB Q3_K_M Tight
25.5 tok/s

22–31

A800 PCIe 40 GB NVIDIA 40 GB 1,560 GB/s Nov 2022 33.0 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 73.8 GB Q8_0 Comfortable
25.1 tok/s

15–40 · low confidence

Radeon Instinct MI300X AMD 192 GB 5,325 GB/s Dec 2023 73.8 GB Q8_0 Comfortable
25.1 tok/s

15–40 · low confidence

Radeon Instinct MI308X AMD 192 GB 5,325 GB/s Dec 2023 73.8 GB Q8_0 Comfortable
23.8 tok/s

20–29

H100 NVL 94 GB NVIDIA 94 GB 3,940 GB/s Mar 2023 73.8 GB Q8_0 Tight
20.3 tok/s

17–24

H100 PCIe 96 GB NVIDIA 96 GB 3,360 GB/s Mar 2023 73.8 GB Q8_0 Tight
20.3 tok/s

17–24

H100 SXM5 94 GB NVIDIA 94 GB 3,360 GB/s Mar 2023 73.8 GB Q8_0 Tight
20.3 tok/s

17–24

H100 SXM5 96 GB NVIDIA 96 GB 3,360 GB/s Mar 2023 73.8 GB Q8_0 Tight
18.7 tok/s

16–22

RTX PRO 5000 Blackwell NVIDIA 48 GB 1,340 GB/s Mar 2025 41.2 GB Q4_K_M Tight
17.9 tok/s

15–22

A100 SXM4 80 GB NVIDIA 80 GB 2,040 GB/s Nov 2020 57.5 GB Q6_K Comfortable
17.9 tok/s

15–22

A100X NVIDIA 80 GB 2,040 GB/s Jun 2021 57.5 GB Q6_K Comfortable
17.9 tok/s

15–22

A800 SXM4 80 GB NVIDIA 80 GB 2,040 GB/s Aug 2022 57.5 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
DeepSeek
Organisation type
Industry
Country
China
Published
22 January 2025
Authors
DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, Xiaokang Zhang, Xingkai Yu, Yu Wu, Z.F. Wu, Zhibin Gou, Zhihong Shao, Zhuoshu Li, Ziyi Gao, Aixin Liu, Bing Xue, Bingxuan Wang, Bochao Wu, Bei Feng, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, Damai Dai, Deli Chen, Dongjie Ji, Erhang Li, Fangyu…

What it does

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

Domain
Language
Task
Language modeling/generation, Question answering, Quantitative reasoning, Code generation
Base model
Llama 3.3 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
24,000,000,000 tokens

"To equip more efficient smaller models with reasoning capabilities like DeepSeek-R1, we directly fine-tuned open-source models like Qwen (Qwen, 2024b) and Llama (AI@Meta, 2024) using the 800k samples curated with DeepSeek-R1, as detailed in §2.3.3" assuming ~30000 tokens per sample 30000 * 800000 = 24 000 000 000 tokens (speculative)

Epochs
2

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
2 × 10²² FLOP

6 FLOP / token / parameter * 70 * 10^9 parameters * 24 * 10^9 tokens * 2 epochs = 2.016e+22 FLOP (speculative since number of tokens could be +- 1 OOM)

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
Unreleased

https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B MIT license

Hugging Face
deepseek-ai

How it is classified

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

Record confidence
Speculative

Sources

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

Reference
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Last updated
28 November 2025

The extremes

The ten fastest GPUs that run DeepSeek-R1-Distill-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 DeepSeek-R1-Distill-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 33.0 GB · Q3_K_M · tight 25.5 tok/s
  2. 02 A100 PCIe 40 GB 40 GB · needs 33.0 GB · Q3_K_M · tight 25.5 tok/s
  3. 03 A100 SXM4 40 GB 40 GB · needs 33.0 GB · Q3_K_M · tight 25.5 tok/s
  4. 04 Radeon PRO W7900D 48 GB · needs 41.2 GB · Q4_K_M · tight 9.4 tok/s
  5. 05 RTX PRO 5000 Blackwell 48 GB · needs 41.2 GB · Q4_K_M · tight 18.7 tok/s
  6. 06 RTX 5880 Ada Generation 48 GB · needs 41.2 GB · Q4_K_M · tight 12.1 tok/s
  7. 07 L20 48 GB · needs 41.2 GB · Q4_K_M · tight 12.1 tok/s
  8. 08 Radeon PRO W7800 48 GB 48 GB · needs 41.2 GB · Q4_K_M · tight 9.4 tok/s
  9. 09 Radeon PRO W7900 48 GB · needs 41.2 GB · Q4_K_M · tight 9.4 tok/s
  10. 10 Data Center GPU Max 1100 48 GB · needs 41.2 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

33.0 GB

Fastest

48.4 tok/s

DeepSeek-R1-Distill-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, Q3_K_M compression, roughly 25.5 tokens per second.

A B200 is the fastest we calculate for it: about 48.4 tokens per second, from 8,000 GB/s of memory bandwidth.

Where it came from

DeepSeek-R1-Distill-Llama-70B was published by DeepSeek, in China, in January 2025. It comes out of industry.

It works in Language, and is recorded as doing language modeling/generation, Question answering, Quantitative reasoning, Code generation.

It is derived from Llama 3.3 70B rather than trained from scratch, which is the usual way a specialised model is produced.

The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached. It is published under the deepseek-ai organisation on Hugging Face.

Understanding the speeds

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.

Training and provenance

Around 24,000,000,000 tokens went into training it.

Step by step

How to choose a GPU for DeepSeek-R1-Distill-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 DeepSeek-R1-Distill-Llama-70B — around 33.0 GB at Q3_K_M. Capacity is the gate — a card either holds it or it does not.

  2. 02

    Match the context to your actual use

    The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect: at long context DeepSeek-R1-Distill-Llama-70B can slip off a card that handles short questions easily.

  3. 03

    Decide how much compression you will accept

    Compression is what makes DeepSeek-R1-Distill-Llama-70B fit smaller cards, at some cost in accuracy — Q3_K_M on the smallest card that fits. A minimum quality removes the ones that go too far.

  4. 04

    Compare tokens per second, not specifications

    Sort by speed to see how cards rank for DeepSeek-R1-Distill-Llama-70B. It will not match a gaming ordering — generation is bound by memory bandwidth, 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 DeepSeek-R1-Distill-Llama-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

    Each card page repeats this sweep for every model we hold. It answers what else the hardware is good for, beyond DeepSeek-R1-Distill-Llama-70B.

Answers

DeepSeek-R1-Distill-Llama-70B — common questions

01

Who created DeepSeek-R1-Distill-Llama-70B?

DeepSeek-R1-Distill-Llama-70B was published by DeepSeek, based in China, categorised as industry.

02

When was DeepSeek-R1-Distill-Llama-70B released?

DeepSeek-R1-Distill-Llama-70B was published in January 2025.

03

What is DeepSeek-R1-Distill-Llama-70B used for?

DeepSeek-R1-Distill-Llama-70B works in Language, and is recorded as handling language modeling/generation, Question answering, Quantitative reasoning, Code generation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

04

Where can I download DeepSeek-R1-Distill-Llama-70B?

Its weights are published under the deepseek-ai organisation on Hugging Face. We do not host model files — this site calculates what hardware is needed to run them.

05

Can I run DeepSeek-R1-Distill-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 12.4 GB. Our figures for DeepSeek-R1-Distill-Llama-70B assume it is fully resident.

06

Would two GPUs run DeepSeek-R1-Distill-Llama-70B faster?

A second card roughly doubles the memory available but not the generation rate. With 61 cards already able to run DeepSeek-R1-Distill-Llama-70B alone, the case for pairing is weak.

07

Why does the quantisation differ between cards for DeepSeek-R1-Distill-Llama-70B?

Because capacity varies, so does how hard DeepSeek-R1-Distill-Llama-70B has to be squeezed — 4 distinct levels appear in the table above. Set a minimum quality to compare at one.

08

How accurate are these DeepSeek-R1-Distill-Llama-70B speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 41–58 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.

09

What GPU do I need to run DeepSeek-R1-Distill-Llama-70B?

The smallest card in our catalogue that holds DeepSeek-R1-Distill-Llama-70B is the A100 PCIe 40 GB, with 40 GB of memory. It runs the model at Q3_K_M using about 33.0 GB, and produces roughly 25.5 tokens per second. 61 cards in total can run it.

10

How fast is DeepSeek-R1-Distill-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 DeepSeek-R1-Distill-Llama-70B clear that.

11

How much VRAM does DeepSeek-R1-Distill-Llama-70B need?

About 33.0 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.

12

Is DeepSeek-R1-Distill-Llama-70B open source?

Its weights are published, so DeepSeek-R1-Distill-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.

13

How many parameters does DeepSeek-R1-Distill-Llama-70B have?

DeepSeek-R1-Distill-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.

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