Qwen3.5-122B-A10B TPS calculator

Open weights Alibaba 122B 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

43 cards that can run it

818 cards we hold specifications for

Smallest card that fits

Radeon Instinct MI200

64 GB · Q3_K_M · 66.6 tok/s

Fastest card

B200

154 tok/s · 180 GB

Which GPUs can run Qwen3.5-122B-A10B?

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

43 cards match

Calculating

					Needs	Quantisation	Fit
154 tok/s 93–247 · low confidence	B200 NVIDIA	180 GB	8,000 GB/s	Jan 2024	124.1 GB	Q8_0	Comfortable
154 tok/s 93–247 · low confidence	B300 NVIDIA	288 GB	8,000 GB/s	Sep 2025	124.1 GB	Q8_0	Comfortable
150 tok/s 90–239 · low confidence	H100 SXM5 80 GB NVIDIA	80 GB	3,360 GB/s	Oct 2022	67.3 GB	Q4_K_M	Tight
150 tok/s 90–239 · low confidence	H800 SXM5 NVIDIA	80 GB	3,360 GB/s	Mar 2023	67.3 GB	Q4_K_M	Tight
143 tok/s 86–229 · low confidence	Radeon Instinct MI300 AMD	128 GB	6,550 GB/s	Jan 2023	95.7 GB	Q6_K	Comfortable
136 tok/s 81–217 · low confidence	H100 NVL 94 GB NVIDIA	94 GB	3,940 GB/s	Mar 2023	81.5 GB	Q5_K_M	Tight
123 tok/s 74–197 · low confidence	Radeon Instinct MI350X AMD	288 GB	8,190 GB/s	Jan 2025	124.1 GB	Q8_0	Comfortable
123 tok/s 74–197 · low confidence	Radeon Instinct MI355X AMD	288 GB	8,190 GB/s	Jan 2025	124.1 GB	Q8_0	Comfortable
116 tok/s 70–186 · low confidence	Radeon Instinct MI300A AMD	128 GB	5,325 GB/s	Dec 2023	95.7 GB	Q6_K	Comfortable
116 tok/s 69–185 · low confidence	H100 PCIe 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	81.5 GB	Q5_K_M	Tight
116 tok/s 69–185 · low confidence	H100 SXM5 94 GB NVIDIA	94 GB	3,360 GB/s	Mar 2023	81.5 GB	Q5_K_M	Tight
116 tok/s 69–185 · low confidence	H100 SXM5 96 GB NVIDIA	96 GB	3,360 GB/s	Mar 2023	81.5 GB	Q5_K_M	Tight
105 tok/s 63–168 · low confidence	H100 SXM5 64 GB NVIDIA	64 GB	2,020 GB/s	Mar 2023	53.1 GB	Q3_K_M	Tight
94.3 tok/s 57–151 · low confidence	H200 NVL NVIDIA	141 GB	4,890 GB/s	Nov 2024	124.1 GB	Q8_0	Tight
94.3 tok/s 57–151 · low confidence	H200 SXM 141 GB NVIDIA	141 GB	4,890 GB/s	Nov 2024	124.1 GB	Q8_0	Tight
90.8 tok/s 55–145 · low confidence	A100 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Nov 2020	67.3 GB	Q4_K_M	Tight
90.8 tok/s 55–145 · low confidence	A100X NVIDIA	80 GB	2,040 GB/s	Jun 2021	67.3 GB	Q4_K_M	Tight
90.8 tok/s 55–145 · low confidence	A800 SXM4 80 GB NVIDIA	80 GB	2,040 GB/s	Aug 2022	67.3 GB	Q4_K_M	Tight
90.8 tok/s 55–145 · low confidence	H100 CNX NVIDIA	80 GB	2,040 GB/s	Mar 2023	67.3 GB	Q4_K_M	Tight
90.8 tok/s 55–145 · low confidence	H100 PCIe 80 GB NVIDIA	80 GB	2,040 GB/s	Oct 2022	67.3 GB	Q4_K_M	Tight
90.8 tok/s 55–145 · low confidence	H800 PCIe 80 GB NVIDIA	80 GB	2,040 GB/s	Mar 2023	67.3 GB	Q4_K_M	Tight
90.3 tok/s 54–144 · low confidence	Radeon Instinct MI325X AMD	256 GB	6,000 GB/s	Oct 2024	124.1 GB	Q8_0	Comfortable
86.4 tok/s 52–138 · low confidence	A100 PCIe 80 GB NVIDIA	80 GB	1,940 GB/s	Jun 2021	67.3 GB	Q4_K_M	Tight
86.4 tok/s 52–138 · low confidence	A800 PCIe 80 GB NVIDIA	80 GB	1,940 GB/s	Nov 2022	67.3 GB	Q4_K_M	Tight
80.1 tok/s 48–128 · low confidence	Radeon Instinct MI300X AMD	192 GB	5,325 GB/s	Dec 2023	124.1 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: 24 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

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: 122B
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 (restricted use)
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: Qwen3.5: Towards Native Multimodal Agents
Last updated: 8 April 2026

The extremes

The ten fastest GPUs that run Qwen3.5-122B-A10B

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 Qwen3.5-122B-A10B

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 it takes to run this model

Minimum card

Radeon Instinct MI200

Memory needed

53.1 GB

Fastest

154 tok/s

Qwen3.5-122B-A10B reaches a parameter count of 122B. 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: 43.

The smallest card that holds it is Radeon Instinct MI200, with a memory capacity of 64 GB, running it at a compression of Q3_K_M and producing around 66.6 tokens per second.

The fastest we calculate for it is B200, generating roughly 154 tokens per second on the strength of a memory bandwidth of 8,000 GB/s.

What this model is

Qwen3.5-122B-A10B was published by Alibaba, in the country recorded as China, during February 2026. It comes out of an organisation categorised as industry.

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

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.

What decides the speed

Half the cards that hold it manage more than 90.3 tokens per second. Producing text faster than most people read it: 41 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.

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.

What went into building it

Its inclusion criterion: discretionary.

Step by step

How to choose a GPU for Qwen3.5-122B-A10B

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

The table lists every card able to hold Qwen3.5-122B-A10B, needing around 53.1 GB at a compression of Q3_K_M. 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, because at long context a card that handles short questions easily can be dropped by Qwen3.5-122B-A10B.
03

Set a quality floor

Each card runs the least-compressed copy it can hold, 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 Qwen3.5-122B-A10B. It will not match a gaming ordering, because generation is bound by memory bandwidth. The card topping the list is B200, at 154 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 Qwen3.5-122B-A10B. 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

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 you have settled on Qwen3.5-122B-A10B.

Answers

Qwen3.5-122B-A10B — common questions

Qwen3.5-122B-A10B— 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.

Qwen3.5-122B-A10B— how many parameters does it have?

It has a parameter count of 122B. 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.

Qwen3.5-122B-A10B— who created it?

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

Qwen3.5-122B-A10B— when was it released?

It was published in February 2026.

Qwen3.5-122B-A10B— what is it used for?

It works in the domain of Language, and is recorded as handling the task of language modeling/generation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

Qwen3.5-122B-A10B— 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.

Qwen3.5-122B-A10B— can I run it if it does not fit in my GPU?

Partly. Layers that do not fit sit in system memory and run at a fraction of the speed, so a mostly-offloaded model is rarely worth using. The nearest miss we calculate falls short by 24.1 GB. Every figure here assumes the whole model is resident on the card.

Qwen3.5-122B-A10B— would two GPUs run it faster?

Capacity adds across cards; throughput does not. The number of cards already holding it on their own: 43. So a second card is rarely the answer here.

Qwen3.5-122B-A10B— 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.

Qwen3.5-122B-A10B— 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: 93–247 tok/s on B200. The same model and card vary by thirty to fifty per cent depending on the inference software and its version.

Qwen3.5-122B-A10B— what GPU do I need to run it?

The smallest card in our catalogue that holds it is Radeon Instinct MI200, with a memory capacity of 64 GB. It runs the model at a compression of Q3_K_M using about 53.1 GB, and produces roughly 66.6 tokens per second. The number of cards able to run it in total: 43.

Qwen3.5-122B-A10B— how fast is it on a GPU?

It depends on the card. The quickest we calculate is B200, at about 154 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: 41.

Qwen3.5-122B-A10B— how much VRAM does it need?

It needs about 53.1 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.

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