DeepSeek-R1-Distill-Qwen-14B TPS calculator

Open weights DeepSeek 14.8B 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

306 cards that can run it

818 cards we hold specifications for

Smallest card that fits

P102-101

10 GB · Q3_K_M · 21.0 tok/s

Fastest card

B200

229 tok/s · 180 GB

Which GPUs can run DeepSeek-R1-Distill-Qwen-14B?

Set the inputs, read the answer

Context length tokens

A longer conversation needs more memory, which can push this model off smaller cards.

Minimum quality

Hides cards that would only fit the model by compressing it below this point.

Search cards

Card memory

Also show cards that cannot run it

306 cards match

Calculating

					Needs	Quantisation	Fit
229 tok/s 195–275	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	17.1 GB	Q8_0	Comfortable
229 tok/s 195–275	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	17.1 GB	Q8_0	Comfortable
183 tok/s 110–293 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	17.1 GB	Q8_0	Comfortable
183 tok/s 110–293 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	17.1 GB	Q8_0	Comfortable
146 tok/s 88–234 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	17.1 GB	Q8_0	Comfortable
140 tok/s 119–168	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	17.1 GB	Q8_0	Comfortable
140 tok/s 119–168	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	17.1 GB	Q8_0	Comfortable
134 tok/s 80–214 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	17.1 GB	Q8_0	Comfortable
120 tok/s 102–145	CMP 170HX 10 GB NVIDIA	10 GB	1,560 GB/s	Sep 2021	8.5 GB	Q3_K_M	Tight
119 tok/s 71–190 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	17.1 GB	Q8_0	Comfortable
119 tok/s 71–190 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	17.1 GB	Q8_0	Comfortable
119 tok/s 71–190 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	17.1 GB	Q8_0	Comfortable
113 tok/s 96–135	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	17.1 GB	Q8_0	Comfortable
96.2 tok/s 82–115	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	17.1 GB	Q8_0	Comfortable
96.2 tok/s 82–115	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	17.1 GB	Q8_0	Comfortable
96.2 tok/s 82–115	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	17.1 GB	Q8_0	Comfortable
96.2 tok/s 82–115	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	17.1 GB	Q8_0	Comfortable
96.2 tok/s 82–115	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	17.1 GB	Q8_0	Comfortable
73.2 tok/s 44–117 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	17.1 GB	Q8_0	Comfortable
73.2 tok/s 44–117 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	17.1 GB	Q8_0	Comfortable
61.0 tok/s 37–98 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	17.1 GB	Q8_0	Comfortable
60.3 tok/s 51–72	GeForce RTX 3080 12 GB NVIDIA	12 GB	912 GB/s	Jan 2022	10.2 GB	Q4_K_M	Tight
60.3 tok/s 51–72	GeForce RTX 3080 Ti NVIDIA	12 GB	912 GB/s	May 2021	10.2 GB	Q4_K_M	Tight
59.7 tok/s 36–96 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	17.1 GB	Q8_0	Comfortable
58.7 tok/s 50–70	CMP 90HX NVIDIA	10 GB	760 GB/s	Jul 2021	8.5 GB	Q3_K_M	Tight

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, Quantitative reasoning, Question answering, Mathematical reasoning, Code generation
Base model: Qwen2.5-14B

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: 14.8B
Training data: 24,000,000,000 tokens
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: 4.3 × 10²¹ FLOP

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
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-Qwen-14B

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.

The smallest GPUs that still run DeepSeek-R1-Distill-Qwen-14B

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

What the numbers mean

What you need to run it

Minimum card

P102-101

Memory needed

8.5 GB

Fastest

229 tok/s

DeepSeek-R1-Distill-Qwen-14B is small enough at 14.8B parameters that hardware is rarely the obstacle — 306 of the cards we track can run it, including cards several years old.

The least hardware that works is a P102-101. Its 10 GB is enough at Q3_K_M compression, giving roughly 21.0 tokens per second.

Top of the range is the B200, at roughly 229 tokens per second thanks to 8,000 GB/s of bandwidth.

Where it came from

DeepSeek-R1-Distill-Qwen-14B was published by DeepSeek, in China, in January 2025. The organisation is categorised as industry.

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

It builds on Qwen2.5-14B, which is why it shares that model's general shape and size.

The weights being open is what puts this page in the calculator rather than only in the catalogue: it is a model you can actually hold. It is published under the deepseek-ai organisation on Hugging Face.

Understanding the speeds

Across every card that can run it, the middle of the range is about 21.4 tokens per second, and 266 of them clear the ten tokens per second that roughly matches reading speed.

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.

Its attention layout is on file, so the memory figures are computed exactly rather than approximated.

What went into building it

It was trained on about 24,000,000,000 tokens of text.

Step by step

How to choose a GPU for DeepSeek-R1-Distill-Qwen-14B

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

01

Check what it needs before anything else

The table lists every card that can hold DeepSeek-R1-Distill-Qwen-14B — around 8.5 GB at Q3_K_M. That figure, not the card's headline performance, is what decides whether it runs.
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 DeepSeek-R1-Distill-Qwen-14B stops fitting a card that seemed fine.
03

Decide how much compression you will accept

The quantisation column varies by card, because a bigger card holds a more accurate copy of DeepSeek-R1-Distill-Qwen-14B — Q3_K_M on the smallest card that fits. Set a floor to hold the comparison at one level.
04

Compare tokens per second, not specifications

Sort by speed to see how cards rank for DeepSeek-R1-Distill-Qwen-14B. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 229 tok/s.
05

Check the fit verdict before buying

A tight fit runs DeepSeek-R1-Distill-Qwen-14B but leaves nothing spare for a longer conversation; comfortable has headroom. If you expect to grow the context, buy for comfortable.
06

See what else that card runs

Following a card through to its own page shows every other model it can hold, which is the question that follows once DeepSeek-R1-Distill-Qwen-14B is settled.

Answers

DeepSeek-R1-Distill-Qwen-14B — common questions

When was DeepSeek-R1-Distill-Qwen-14B released?

DeepSeek-R1-Distill-Qwen-14B was published in January 2025.

What is DeepSeek-R1-Distill-Qwen-14B used for?

DeepSeek-R1-Distill-Qwen-14B works in Language, and is recorded as handling language modeling/generation, Quantitative reasoning, Question answering, Mathematical reasoning, Code generation. These are the areas it was designed around; they describe intent rather than a hard boundary.

Where can I download DeepSeek-R1-Distill-Qwen-14B?

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.

Can I run DeepSeek-R1-Distill-Qwen-14B if it does not fit in my GPU?

It can be split between the card and system memory, but DeepSeek-R1-Distill-Qwen-14B generates painfully slowly that way — the nearest miss we calculate is short by 3.0 GB. Nothing on this page assumes offloading.

Would two GPUs run DeepSeek-R1-Distill-Qwen-14B faster?

Two cards buy memory rather than speed. That matters for DeepSeek-R1-Distill-Qwen-14B only if one card cannot hold it — 306 can, so a second adds little.

Why does the quantisation differ between cards for DeepSeek-R1-Distill-Qwen-14B?

A larger card holds a more accurate copy. Across the cards that run DeepSeek-R1-Distill-Qwen-14B, 5 compression levels are used; the floor control above pins it to one.

How accurate are these DeepSeek-R1-Distill-Qwen-14B speed estimates?

Every figure is derived from memory bandwidth and model size, not benchmarked. That is why each is published as a range such as 195–275 tok/s on the B200 rather than a single number.

What GPU do I need to run DeepSeek-R1-Distill-Qwen-14B?

The smallest card in our catalogue that holds DeepSeek-R1-Distill-Qwen-14B is the P102-101, with 10 GB of memory. It runs the model at Q3_K_M using about 8.5 GB, and produces roughly 21.0 tokens per second. 306 cards in total can run it.

How fast is DeepSeek-R1-Distill-Qwen-14B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 229 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 266 of the cards that can run DeepSeek-R1-Distill-Qwen-14B clear that.

How much VRAM does DeepSeek-R1-Distill-Qwen-14B need?

About 8.5 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.

Can I run DeepSeek-R1-Distill-Qwen-14B on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q4_K_M, using about 10.2 GB and generating roughly 60.3 tokens per second — a tight fit.

Can I run DeepSeek-R1-Distill-Qwen-14B on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q6_K, using about 13.7 GB and generating roughly 47.0 tokens per second — a tight fit.

Can I run DeepSeek-R1-Distill-Qwen-14B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 17.1 GB and generating roughly 38.4 tokens per second — a comfortable fit.

Is DeepSeek-R1-Distill-Qwen-14B open source?

Its weights are published, so DeepSeek-R1-Distill-Qwen-14B 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 DeepSeek-R1-Distill-Qwen-14B have?

DeepSeek-R1-Distill-Qwen-14B has 14.8B parameters. 14.8B (safetensors). 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 DeepSeek-R1-Distill-Qwen-14B?

DeepSeek-R1-Distill-Qwen-14B was published by DeepSeek, based in China, categorised as industry.

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