Qwen3-Coder-Next TPS calculator

Open weights Alibaba 80B parameters February 2026

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 · 124 tok/s

Fastest card

B200

235 tok/s · 180 GB

Which GPUs can run Qwen3-Coder-Next?

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

61 cards match

Calculating

					Needs	Quantisation	Fit
235 tok/s 141–376 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	80.7 GB	Q8_0	Comfortable
235 tok/s 141–376 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	80.7 GB	Q8_0	Comfortable
188 tok/s 113–301 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	80.7 GB	Q8_0	Comfortable
188 tok/s 113–301 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	80.7 GB	Q8_0	Comfortable
150 tok/s 90–240 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	80.7 GB	Q8_0	Comfortable
144 tok/s 86–230 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	80.7 GB	Q8_0	Comfortable
144 tok/s 86–230 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	80.7 GB	Q8_0	Comfortable
144 tok/s 86–230 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	62.0 GB	Q6_K	Tight
144 tok/s 86–230 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	62.0 GB	Q6_K	Tight
138 tok/s 83–220 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	80.7 GB	Q8_0	Comfortable
135 tok/s 81–216 · low confidence	GRID A100B NVIDIA	48 GB	1,870 GB/s	May 2020	38.8 GB	IQ4_XS	Tight
124 tok/s 74–198 · low confidence	A100 PCIe 40 GB NVIDIA	40 GB	1,560 GB/s	Jun 2020	34.1 GB	Q3_K_M	Tight
124 tok/s 74–198 · low confidence	A100 SXM4 40 GB NVIDIA	40 GB	1,560 GB/s	May 2020	34.1 GB	Q3_K_M	Tight
124 tok/s 74–198 · low confidence	A800 PCIe 40 GB NVIDIA	40 GB	1,560 GB/s	Nov 2022	34.1 GB	Q3_K_M	Tight
122 tok/s 73–195 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	80.7 GB	Q8_0	Comfortable
122 tok/s 73–195 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	80.7 GB	Q8_0	Comfortable
122 tok/s 73–195 · low confidence	Radeon Instinct MI308X AMD	192 GB	5,325 GB/s	Dec 2023	80.7 GB	Q8_0	Comfortable
116 tok/s 70–185 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	80.7 GB	Q8_0	Tight
106 tok/s 64–170 · low confidence	H100 SXM5 64 GB NVIDIA	64 GB	2,020 GB/s	Mar 2023	52.7 GB	Q5_K_M	Tight
98.8 tok/s 59–158 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	80.7 GB	Q8_0	Tight
98.8 tok/s 59–158 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	80.7 GB	Q8_0	Tight
98.8 tok/s 59–158 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	80.7 GB	Q8_0	Tight
96.8 tok/s 58–155 · low confidence	RTX PRO 5000 Blackwell NVIDIA	48 GB	1,340 GB/s	Mar 2025	38.8 GB	IQ4_XS	Tight
87.2 tok/s 52–139 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	62.0 GB	Q6_K	Tight
87.2 tok/s 52–139 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	62.0 GB	Q6_K	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: 2 February 2026

What it does

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

Domain: Language
Task: Language modeling/generation, Coding
Base model: Qwen3-Next-80B-A3B

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: 80B
Training data: tokens

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)
Hugging Face: Qwen

How it is classified

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

Why it is tracked: Discretionary
Record confidence: Likely

Sources

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

Reference: Qwen3-Coder-Next: Pushing Small Hybrid Models on Agentic Coding
Last updated: 8 April 2026

The extremes

The ten fastest GPUs that run Qwen3-Coder-Next

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 Qwen3-Coder-Next

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

A100 PCIe 40 GB

Memory needed

34.1 GB

Fastest

235 tok/s

Qwen3-Coder-Next reaches a parameter count of 80B. That puts it above consumer hardware, into the range where a card is bought for this purpose rather than repurposed for it. The number of cards we track that can hold it: 61.

The least hardware that works is A100 PCIe 40 GB, with a memory capacity of 40 GB, running it at a compression of Q3_K_M and producing around 124 tokens per second.

The fastest we calculate for it is B200, generating roughly 235 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

About this model

Qwen3-Coder-Next was published by Alibaba, in the country recorded as China, during February 2026. The category the publisher falls under is industry.

It works in the domain of Language, and is recorded as performing the task of language modeling/generation, Coding.

Rather than being trained from scratch, it is derived from Qwen3-Next-80B-A3B. That is the usual way a specialised model is produced.

Published weights mean the model runs on your machine rather than someone else's, which is what makes the hardware question below answerable at all. On Hugging Face it is published under the organisation Qwen.

How fast it runs, and why

Half the cards that hold it manage more than 82.9 tokens per second. Producing text faster than most people read it: 59 of them.

Because it routes each token through a subset of its weights, it produces text at the pace of a much smaller model. The catch is memory: all of it still has to fit, so the speed is a bonus rather than a discount on hardware.

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.

Training and provenance

Its inclusion criterion: discretionary.

Step by step

How to choose a GPU for Qwen3-Coder-Next

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 able to hold Qwen3-Coder-Next, needing around 34.1 GB at a compression of Q3_K_M. That figure, not the headline performance of a card, is what decides whether it runs.
02

Set the context length you will work at

Longer conversations cost memory on top of what the weights need. Move the slider to your real working length before trusting any row for Qwen3-Coder-Next.
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

Ranking by tokens per second follows memory bandwidth rather than core counts, for Qwen3-Coder-Next. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 235 tok/s.
05

Check the fit verdict before buying

Tight means it loads and works with no room to raise the context later, in the case of Qwen3-Coder-Next. 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 Qwen3-Coder-Next.

Answers

Qwen3-Coder-Next — common questions

Qwen3-Coder-Next— would two GPUs run it faster?

Two cards buy memory rather than speed, which matters only if one card cannot hold it. The number that can: 61. So a second card is rarely the answer here.

Qwen3-Coder-Next— 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: 5. Bigger cards get the more accurate version, and the quality floor above pins the comparison to one level.

Qwen3-Coder-Next— how accurate are these speed estimates?

These are estimates with real error bars, and any of them could reasonably land anywhere in its published range depending on which runtime you use. The fastest result here: 141–376 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

Qwen3-Coder-Next— what GPU do I need to run it?

The smallest card in our catalogue that holds it is A100 PCIe 40 GB, with a memory capacity of 40 GB. It runs the model at a compression of Q3_K_M using about 34.1 GB, and produces roughly 124 tokens per second. The number of cards able to run it in total: 61.

Qwen3-Coder-Next— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 235 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: 59.

Qwen3-Coder-Next— how much VRAM does it need?

It needs about 34.1 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.

Qwen3-Coder-Next— 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.

Qwen3-Coder-Next— how many parameters does it have?

It has a parameter count of 80B. Finetune of Qwen3-Next-80B-A3B, which has 80 billion parameters. 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.

Qwen3-Coder-Next— who created it?

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

Qwen3-Coder-Next— when was it released?

It was published in February 2026.

Qwen3-Coder-Next— what is it used for?

It works in the domain of Language, and is recorded as handling the task of language modeling/generation, Coding. 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.

Qwen3-Coder-Next— 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.

Qwen3-Coder-Next— can I run it if it does not fit in my GPU?

It can be split between the card and system memory, but it generates painfully slowly that way. The nearest miss we calculate falls short by 14.6 GB. Every figure here assumes the whole model is resident on the card.

Source

Original publication

Record last updated 8 April 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