Qwen2.5-Coder (32B) TPS calculator

Open weights Alibaba 32.5B parameters November 2024

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

132 cards that can run it

818 cards we hold specifications for

Smallest card that fits

RTX A4500

20 GB · Q3_K_M · 22.5 tok/s

Fastest card

B200

104 tok/s · 180 GB

Which GPUs can run Qwen2.5-Coder (32B)?

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

132 cards match

Calculating

					Needs	Quantisation	Fit
104 tok/s 89–125	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	35.5 GB	Q8_0	Comfortable
104 tok/s 89–125	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	35.5 GB	Q8_0	Comfortable
83.3 tok/s 50–133 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	35.5 GB	Q8_0	Comfortable
83.3 tok/s 50–133 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	35.5 GB	Q8_0	Comfortable
66.6 tok/s 40–107 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	35.5 GB	Q8_0	Comfortable
63.7 tok/s 54–76	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	35.5 GB	Q8_0	Comfortable
63.7 tok/s 54–76	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	35.5 GB	Q8_0	Comfortable
61.0 tok/s 37–98 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	35.5 GB	Q8_0	Comfortable
54.1 tok/s 32–87 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	35.5 GB	Q8_0	Comfortable
54.1 tok/s 32–87 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	35.5 GB	Q8_0	Comfortable
54.1 tok/s 32–87 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	35.5 GB	Q8_0	Comfortable
51.3 tok/s 44–62	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	35.5 GB	Q8_0	Comfortable
43.8 tok/s 37–53	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	35.5 GB	Q8_0	Comfortable
43.8 tok/s 37–53	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	35.5 GB	Q8_0	Comfortable
43.8 tok/s 37–53	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	35.5 GB	Q8_0	Comfortable
43.8 tok/s 37–53	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	35.5 GB	Q8_0	Comfortable
43.8 tok/s 37–53	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	35.5 GB	Q8_0	Comfortable
40.3 tok/s 34–48	GeForce RTX 5090 D V2 NVIDIA	24 GB	1,340 GB/s	Aug 2025	20.3 GB	Q4_K_M	Tight
36.7 tok/s 31–44	A30X NVIDIA	24 GB	1,220 GB/s	Apr 2021	20.3 GB	Q4_K_M	Tight
35.4 tok/s 30–42	DRIVE A100 PROD NVIDIA	32 GB	1,870 GB/s	May 2020	27.9 GB	Q6_K	Tight
35.4 tok/s 30–42	GRID A100A NVIDIA	32 GB	1,870 GB/s	May 2020	27.9 GB	Q6_K	Tight
33.9 tok/s 29–41	GeForce RTX 5090 NVIDIA	32 GB	1,790 GB/s	Jan 2025	27.9 GB	Q6_K	Tight
33.9 tok/s 29–41	GeForce RTX 5090 D NVIDIA	32 GB	1,790 GB/s	Jan 2025	27.9 GB	Q6_K	Tight
33.3 tok/s 20–53 · low confidence	Radeon Instinct MI250 AMD	128 GB	3,280 GB/s	Nov 2021	35.5 GB	Q8_0	Comfortable
33.3 tok/s 20–53 · low confidence	Radeon Instinct MI250X AMD	128 GB	3,280 GB/s	Nov 2021	35.5 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: Alibaba
Organisation type: Industry
Country: China
Published: 12 November 2024
Authors: Binyuan Hui, Jian Yang, Zeyu Cui, Jiaxi Yang, Dayiheng Liu, Lei Zhang, Tianyu Liu, Jiajun Zhang, Bowen Yu, Keming Lu, Kai Dang, Yang Fan, Yichang Zhang, An Yang, Rui Men, Fei Huang, Bo Zheng, Yibo Miao, Shanghaoran Quan, Yunlong Feng, Xingzhang Ren, Xuancheng Ren, Jingren Zhou, Junyang Lin

What it does

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

Domain: Language
Task: Language modeling/generation, Code generation

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: 32.5B
Training data: tokens
Epochs: 1

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: 1.1 × 10²⁴ FLOP
How it was established: Operation counting

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Data centre: The paper does not mention any hardware, GPUs or any information regarding the hardware used.

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: Qwen

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: Qwen2.5-Coder Technical Report
Last updated: 11 February 2026

The extremes

The ten fastest GPUs that run Qwen2.5-Coder (32B)

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 Qwen2.5-Coder (32B)

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

Hardware requirements in practice

Minimum card

RTX A4500

Memory needed

16.5 GB

Fastest

104 tok/s

With 32.5B parameters, Qwen2.5-Coder (32B) lands in the range a serious desktop card can handle once the weights are compressed. 132 of the cards we track can run it.

The entry point is the RTX A4500: 20 GB of memory, Q3_K_M compression, roughly 22.5 tokens per second.

The quickest result comes from a B200 at around 104 tokens per second — its 8,000 GB/s of bandwidth is what buys that.

About this model

Qwen2.5-Coder (32B) was published by Alibaba, in China, in November 2024. industry is the category the publisher falls under.

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

Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded. It is published under the Qwen organisation on Hugging Face.

How fast it runs, and why

Across every card that can run it, the middle of the range is about 20.3 tokens per second, and 102 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

Producing it required around 1.1 × 10²⁴ FLOP of arithmetic, which is a statement about the training budget rather than about inference.

Step by step

How to choose a GPU for Qwen2.5-Coder (32B)

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

Every card here has been checked against Qwen2.5-Coder (32B) — around 16.5 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

Set the context to what you will actually use. The cache grows with the conversation, and it is the usual reason Qwen2.5-Coder (32B) stops fitting a card that seemed fine.
03

Decide how much compression you will accept

Compression is what makes Qwen2.5-Coder (32B) 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.
04

Compare tokens per second, not specifications

The speed ordering for Qwen2.5-Coder (32B) is effectively an ordering by memory bandwidth, which is why the B200 tops it at 104 tok/s.
05

Read the fit column last

The fit column separates cards that just manage Qwen2.5-Coder (32B) from those with room to spare. Buy for the second if the context might grow.
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 Qwen2.5-Coder (32B).

Answers

Qwen2.5-Coder (32B) — common questions

What GPU do I need to run Qwen2.5-Coder (32B)?

The smallest card in our catalogue that holds Qwen2.5-Coder (32B) is the RTX A4500, with 20 GB of memory. It runs the model at Q3_K_M using about 16.5 GB, and produces roughly 22.5 tokens per second. 132 cards in total can run it.

How fast is Qwen2.5-Coder (32B) on a GPU?

It depends on the card. The quickest we calculate is a B200 at about 104 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and 102 of the cards that can run Qwen2.5-Coder (32B) clear that.

How much VRAM does Qwen2.5-Coder (32B) need?

About 16.5 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 Qwen2.5-Coder (32B) on a 24 GB GPU?

Yes. A GeForce RTX 5090 D V2 with 24 GB runs it at Q4_K_M, using about 20.3 GB and generating roughly 40.3 tokens per second — a tight fit.

Is Qwen2.5-Coder (32B) open source?

Its weights are published, so Qwen2.5-Coder (32B) 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 Qwen2.5-Coder (32B) have?

Qwen2.5-Coder (32B) has 32.5B parameters. 32.5B (31B - non emb). 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 Qwen2.5-Coder (32B)?

Qwen2.5-Coder (32B) was published by Alibaba, based in China, categorised as industry.

When was Qwen2.5-Coder (32B) released?

Qwen2.5-Coder (32B) was published in November 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 Qwen2.5-Coder (32B) used for?

Qwen2.5-Coder (32B) works in Language, and is recorded as handling language modeling/generation, Code generation. 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 Qwen2.5-Coder (32B)?

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

How much compute was used to train Qwen2.5-Coder (32B)?

Around 1.1 × 10²⁴ FLOP. 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.

Can I run Qwen2.5-Coder (32B) 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 5.9 GB. Our figures for Qwen2.5-Coder (32B) assume it is fully resident.

Would two GPUs run Qwen2.5-Coder (32B) faster?

Two cards buy memory rather than speed. That matters for Qwen2.5-Coder (32B) only if one card cannot hold it — 132 can, so a second adds little.

Why does the quantisation differ between cards for Qwen2.5-Coder (32B)?

Each card is shown running the least-compressed copy it can hold, and Qwen2.5-Coder (32B) appears at 5 different compression levels across the cards that fit it. Bigger cards get the more accurate version.

How accurate are these Qwen2.5-Coder (32B) speed estimates?

They are calculated from specifications rather than measured, and each carries a range — 89–125 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.

Source

Original publication

Record last updated 11 February 2026

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