Qwen2-57B-A14B TPS calculator

Open weights Alibaba 57B parameters June 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

93 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Radeon PRO V710

28 GB · Q3_K_M · 32.1 tok/s

Fastest card

B200

242 tok/s · 180 GB

Which GPUs can run Qwen2-57B-A14B?

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

93 cards match

Calculating

					Needs	Quantisation	Fit
242 tok/s 145–387 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	57.8 GB	Q8_0	Comfortable
242 tok/s 145–387 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	57.8 GB	Q8_0	Comfortable
193 tok/s 116–309 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	57.8 GB	Q8_0	Comfortable
193 tok/s 116–309 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	57.8 GB	Q8_0	Comfortable
155 tok/s 93–247 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	57.8 GB	Q8_0	Comfortable
148 tok/s 89–237 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	57.8 GB	Q8_0	Comfortable
148 tok/s 89–237 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	57.8 GB	Q8_0	Comfortable
142 tok/s 85–227 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	57.8 GB	Q8_0	Comfortable
139 tok/s 83–222 · low confidence	DRIVE A100 PROD NVIDIA	32 GB	1,870 GB/s	May 2020	27.9 GB	IQ4_XS	Tight
139 tok/s 83–222 · low confidence	GRID A100A NVIDIA	32 GB	1,870 GB/s	May 2020	27.9 GB	IQ4_XS	Tight
133 tok/s 80–213 · low confidence	GeForce RTX 5090 NVIDIA	32 GB	1,790 GB/s	Jan 2025	27.9 GB	IQ4_XS	Tight
133 tok/s 80–213 · low confidence	GeForce RTX 5090 D NVIDIA	32 GB	1,790 GB/s	Jan 2025	27.9 GB	IQ4_XS	Tight
126 tok/s 75–201 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	57.8 GB	Q8_0	Comfortable
126 tok/s 75–201 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	57.8 GB	Q8_0	Comfortable
126 tok/s 75–201 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	57.8 GB	Q8_0	Comfortable
119 tok/s 72–191 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	57.8 GB	Q8_0	Comfortable
109 tok/s 65–174 · low confidence	A100 PCIe 40 GB NVIDIA	40 GB	1,560 GB/s	Jun 2020	31.3 GB	Q4_K_M	Tight
109 tok/s 65–174 · low confidence	A100 SXM4 40 GB NVIDIA	40 GB	1,560 GB/s	May 2020	31.3 GB	Q4_K_M	Tight
109 tok/s 65–174 · low confidence	A800 PCIe 40 GB NVIDIA	40 GB	1,560 GB/s	Nov 2022	31.3 GB	Q4_K_M	Tight
102 tok/s 61–163 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	57.8 GB	Q8_0	Comfortable
102 tok/s 61–163 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	57.8 GB	Q8_0	Comfortable
102 tok/s 61–163 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	57.8 GB	Q8_0	Comfortable
102 tok/s 61–163 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	57.8 GB	Q8_0	Comfortable
102 tok/s 61–163 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	57.8 GB	Q8_0	Comfortable
101 tok/s 61–162 · low confidence	GRID A100B NVIDIA	48 GB	1,870 GB/s	May 2020	37.9 GB	Q5_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: Alibaba
Organisation type: Industry
Country: China
Published: 7 June 2024
Authors: An Yang, Baosong Yang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Zhou, Chengpeng Li, Chengyuan Li, Dayiheng Liu, Fei Huang, Guanting Dong, Haoran Wei, Huan Lin, Jialong Tang, Jialin Wang, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Ma, Jianxin Yang, Jin Xu, Jingren Zhou, Jinze Bai, Jinzheng He, Junyang Lin, Kai Dang, Keming Lu, Keqin Chen, Kexin Yang, Mei Li, Mingfeng Xue, Na Ni, Pei Zhang, Peng W…

What it does

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

Domain: Language
Task: Chat, Language modeling/generation, Question answering
Approach: Self-supervised learning

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: 57B
Training data: 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.

Training compute: 3.8 × 10²³ FLOP
How it was established: Operation counting

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: Hello Qwen2
Last updated: 28 November 2025

The extremes

The ten fastest GPUs that run Qwen2-57B-A14B

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 Qwen2-57B-A14B

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

Radeon PRO V710

Memory needed

24.6 GB

Fastest

242 tok/s

Qwen2-57B-A14B reaches a parameter count of 57B. That lands in the range a serious desktop card can handle once the weights are compressed. The number of cards we track that can run it: 93.

The least hardware that works is Radeon PRO V710, with a memory capacity of 28 GB, running it at a compression of Q3_K_M and producing around 32.1 tokens per second.

Top of the range is B200, generating roughly 242 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

About this model

Qwen2-57B-A14B was published by Alibaba, in the country recorded as China, during June 2024. It comes out of an organisation categorised as industry.

It works in the domain of Language, and is recorded as performing the task of chat, Language modeling/generation, Question answering.

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

How fast it runs, and why

Across every card that can run it, the middle of the range sits at 61.7 tokens per second. Producing text faster than most people read it: 90 of them.

This is a mixture-of-experts model, which routes each token through only part of itself. It therefore generates far faster than its total size suggests — while still needing every parameter resident in memory, so it is quick without being cheap to hold.

Because the architecture is recorded, the memory column is derived rather than estimated.

Training and provenance

The training run consumed about 3.8 × 10²³ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.

Step by step

How to choose a GPU for Qwen2-57B-A14B

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

Every card here has been checked against Qwen2-57B-A14B, needing around 24.6 GB at a compression of 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

The conversation occupies memory too, and grows as it goes. Set the slider to the length you expect, because at long context a card that handles short questions easily can be dropped by Qwen2-57B-A14B.
03

Choose how far you will compress it

Compression is what makes a model fit smaller cards, at some cost in accuracy, reaching a compression of Q3_K_M on the smallest card that fits. Setting a minimum quality drops the cards that only manage it by squeezing further than you would want, and holds the comparison at one level.
04

Compare tokens per second, not specifications

Sort by speed to see how cards rank for Qwen2-57B-A14B. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 242 tok/s.
05

Read the fit column last

Tight means it loads and works with no room to raise the context later, in the case of Qwen2-57B-A14B. Comfortable means you can grow the context later. That difference matters more than a few tokens per second, so buy for comfortable if you expect to.
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. A card is usually bought for more than one model, so it is worth a look before buying for Qwen2-57B-A14B.

Answers

Qwen2-57B-A14B — common questions

Qwen2-57B-A14B— where can I download it?

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

Qwen2-57B-A14B— how much compute was used to train it?

Training consumed around 3.8 × 10²³ 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.

Qwen2-57B-A14B— can I run it if it does not fit in my GPU?

Only by offloading, which is usually a false economy: the part held in system memory drags the whole thing down. The nearest miss we calculate falls short by 9.7 GB. Every figure here assumes the whole model is resident on the card.

Qwen2-57B-A14B— would two GPUs run it faster?

A second card roughly doubles the memory available but not the generation rate. The number already able to run it alone: 93. So a second card is rarely the answer here.

Qwen2-57B-A14B— why does the quantisation differ between cards?

A larger card holds a more accurate copy. The number of compression levels used across the cards that run it: 6. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

Qwen2-57B-A14B— how accurate are these speed estimates?

They are calculated from specifications rather than measured, and each carries a range. One example: 145–387 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

Qwen2-57B-A14B— what GPU do I need to run it?

The smallest card in our catalogue that holds it is Radeon PRO V710, with a memory capacity of 28 GB. It runs the model at a compression of Q3_K_M using about 24.6 GB, and produces roughly 32.1 tokens per second. The number of cards able to run it in total: 93.

Qwen2-57B-A14B— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 242 tokens per second; the slowest that still runs it manages considerably less. Reading speed is around ten tokens per second, and the number of cards clearing that: 90.

Qwen2-57B-A14B— how much VRAM does it need?

It needs about 24.6 GB at a compression of Q3_K_M, 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.

Qwen2-57B-A14B— is it open source?

Its weights are published, so it 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.

Qwen2-57B-A14B— how many parameters does it have?

It has a parameter count of 57B. 57B parameters (table 1). 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.

Qwen2-57B-A14B— who created it?

It was published by Alibaba, based in China, an organisation categorised as industry.

Qwen2-57B-A14B— when was it released?

It was published in June 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.

Qwen2-57B-A14B— what is it used for?

It works in the domain of Language, and is recorded as handling the task of chat, Language modeling/generation, Question answering. These are the areas it was designed around; they describe intent rather than a hard boundary.

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