DeepSeek-R1-Distill-Qwen-1.5B TPS calculator

Open weights DeepSeek 1.8B 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

818 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Tesla C1080

4 GB · Q8_0 · 20.7 tok/s

Fastest card

B200

1,904 tok/s · 180 GB

Which GPUs can run DeepSeek-R1-Distill-Qwen-1.5B?

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

818 cards match

Calculating

					Needs	Quantisation	Fit
1,904 tok/s 1,142–3,046 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	2.6 GB	Q8_0	Comfortable
1,904 tok/s 1,142–3,046 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	2.6 GB	Q8_0	Comfortable
1,520 tok/s 912–2,432 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	2.6 GB	Q8_0	Comfortable
1,520 tok/s 912–2,432 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	2.6 GB	Q8_0	Comfortable
1,216 tok/s 729–1,945 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	2.6 GB	Q8_0	Comfortable
1,164 tok/s 698–1,862 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	2.6 GB	Q8_0	Comfortable
1,164 tok/s 698–1,862 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	2.6 GB	Q8_0	Comfortable
1,114 tok/s 668–1,782 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	2.6 GB	Q8_0	Comfortable
988 tok/s 593–1,581 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	2.6 GB	Q8_0	Comfortable
988 tok/s 593–1,581 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	2.6 GB	Q8_0	Comfortable
988 tok/s 593–1,581 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	2.6 GB	Q8_0	Comfortable
937 tok/s 562–1,500 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	2.6 GB	Q8_0	Comfortable
799 tok/s 480–1,279 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	2.6 GB	Q8_0	Comfortable
799 tok/s 480–1,279 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	2.6 GB	Q8_0	Comfortable
799 tok/s 480–1,279 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	2.6 GB	Q8_0	Comfortable
799 tok/s 480–1,279 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	2.6 GB	Q8_0	Comfortable
799 tok/s 480–1,279 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	2.6 GB	Q8_0	Comfortable
609 tok/s 365–974 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	2.6 GB	Q8_0	Comfortable
609 tok/s 365–974 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	2.6 GB	Q8_0	Comfortable
507 tok/s 304–812 · low confidence	Data Center GPU Max 1550 Intel	128 GB	3,280 GB/s	Jan 2023	2.6 GB	Q8_0	Comfortable
496 tok/s 298–794 · low confidence	Data Center GPU Max Subsystem Intel	128 GB	3,210 GB/s	Jan 2023	2.6 GB	Q8_0	Comfortable
485 tok/s 291–777 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	2.6 GB	Q8_0	Comfortable
485 tok/s 291–777 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	2.6 GB	Q8_0	Comfortable
485 tok/s 291–777 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	2.6 GB	Q8_0	Comfortable
485 tok/s 291–777 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	2.6 GB	Q8_0	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, Quantitative reasoning, Question answering, Mathematical reasoning, Code generation
Base model: Qwen2.5-Math-1.5B

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: 1.8B
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: 5.1 × 10²⁰ 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-1.5B

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-1.5B

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

The hardware side

Minimum card

Tesla C1080

Memory needed

2.6 GB

Fastest

1,904 tok/s

DeepSeek-R1-Distill-Qwen-1.5B is small enough at 1.8B parameters that hardware is rarely the obstacle — 818 of the cards we track can run it, including cards several years old.

At the low end, a Tesla C1080 handles it — 4 GB, at Q8_0, for about 20.7 tokens per second.

Top of the range is the B200, at roughly 1,904 tokens per second thanks to 8,000 GB/s of bandwidth.

Background

DeepSeek-R1-Distill-Qwen-1.5B 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, Quantitative reasoning, Question answering, Mathematical reasoning, Code generation.

It is derived from Qwen2.5-Math-1.5B rather than trained from scratch, which is the usual way a specialised model is produced.

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.

Reading the throughput figures

The median result is around 53.5 tokens per second; 792 cards produce text faster than most people read it.

Being dense, it reads all of itself per token, which is why the ordering by speed below follows the ordering by memory bandwidth so closely.

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.

How it was trained

The training set ran to roughly 24,000,000,000 tokens.

Step by step

How to choose a GPU for DeepSeek-R1-Distill-Qwen-1.5B

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

01

Start from the memory column

Look at what DeepSeek-R1-Distill-Qwen-1.5B actually needs — around 2.6 GB at Q8_0. No amount of processing power compensates for a card that cannot hold it.
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-Qwen-1.5B can slip off a card that handles short questions easily.
03

Decide how much compression you will accept

Each card runs the least-compressed copy it can hold — Q8_0 on the smallest card that fits. Setting a floor drops the cards that only manage DeepSeek-R1-Distill-Qwen-1.5B by squeezing it further than you would want.
04

Sort by speed

Sort by speed to see how cards rank for DeepSeek-R1-Distill-Qwen-1.5B. It will not match a gaming ordering — generation is bound by memory bandwidth, which is why the B200 tops it at 1,904 tok/s.
05

Check the fit verdict before buying

The fit column separates cards that just manage DeepSeek-R1-Distill-Qwen-1.5B from those with room to spare. Buy for the second if the context might grow.
06

Check the card from the other side

Each card page repeats this sweep for every model we hold. It answers what else the hardware is good for, beyond DeepSeek-R1-Distill-Qwen-1.5B.

Answers

DeepSeek-R1-Distill-Qwen-1.5B — common questions

How many parameters does DeepSeek-R1-Distill-Qwen-1.5B have?

DeepSeek-R1-Distill-Qwen-1.5B has 1.8B parameters. 1.78B (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-1.5B?

DeepSeek-R1-Distill-Qwen-1.5B was published by DeepSeek, based in China, categorised as industry.

When was DeepSeek-R1-Distill-Qwen-1.5B released?

DeepSeek-R1-Distill-Qwen-1.5B was published in January 2025.

What is DeepSeek-R1-Distill-Qwen-1.5B used for?

DeepSeek-R1-Distill-Qwen-1.5B works in Language, and is recorded as handling language modeling/generation, Quantitative reasoning, Question answering, Mathematical reasoning, Code generation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Where can I download DeepSeek-R1-Distill-Qwen-1.5B?

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-1.5B 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. Our figures for DeepSeek-R1-Distill-Qwen-1.5B assume it is fully resident.

Would two GPUs run DeepSeek-R1-Distill-Qwen-1.5B faster?

Two cards buy memory rather than speed. That matters for DeepSeek-R1-Distill-Qwen-1.5B only if one card cannot hold it — 818 can, so a second adds little.

Why does the quantisation differ between cards for DeepSeek-R1-Distill-Qwen-1.5B?

Each card is shown running the least-compressed copy it can hold, and DeepSeek-R1-Distill-Qwen-1.5B appears at 1 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these DeepSeek-R1-Distill-Qwen-1.5B speed estimates?

These are estimates with real error bars. The fastest result here, 1,142–3,046 tok/s on the B200, could reasonably land anywhere in its published range depending on which runtime you use.

What GPU do I need to run DeepSeek-R1-Distill-Qwen-1.5B?

The smallest card in our catalogue that holds DeepSeek-R1-Distill-Qwen-1.5B is the Tesla C1080, with 4 GB of memory. It runs the model at Q8_0 using about 2.6 GB, and produces roughly 20.7 tokens per second. 818 cards in total can run it.

How fast is DeepSeek-R1-Distill-Qwen-1.5B on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 1,904 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 792 of the cards that can run DeepSeek-R1-Distill-Qwen-1.5B clear that.

How much VRAM does DeepSeek-R1-Distill-Qwen-1.5B need?

About 2.6 GB at Q8_0 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-1.5B on a 8 GB GPU?

Yes. A CMP 170HX 8 GB with 8 GB runs it at Q8_0, using about 2.6 GB and generating roughly 355 tokens per second — a comfortable fit.

Can I run DeepSeek-R1-Distill-Qwen-1.5B on a 12 GB GPU?

Yes. A GeForce RTX 3080 Ti with 12 GB runs it at Q8_0, using about 2.6 GB and generating roughly 217 tokens per second — a comfortable fit.

Can I run DeepSeek-R1-Distill-Qwen-1.5B on a 16 GB GPU?

Yes. A Tesla V100 SXM2 16 GB with 16 GB runs it at Q8_0, using about 2.6 GB and generating roughly 269 tokens per second — a comfortable fit.

Can I run DeepSeek-R1-Distill-Qwen-1.5B on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q8_0, using about 2.6 GB and generating roughly 319 tokens per second — a comfortable fit.

Is DeepSeek-R1-Distill-Qwen-1.5B open source?

Its weights are published, so DeepSeek-R1-Distill-Qwen-1.5B 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.

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