Can I run Qwen3.5-122B-A10B locally?

Yes, the weights are open and hosted at Qwen/Qwen3.5-122B-A10B on Hugging Face, compatible with Transformers, vLLM, SGLang, and KTransformers. You will need substantial VRAM or a multi-GPU setup given the 122B total parameter count.

What does it cost and what is the context window?

Via API it is priced at $0.26 per million input tokens and $2.08 per million output tokens, with a native context of 262,144 tokens.

How does this compare to Qwen3-235B-A22B?

Qwen3.5-122B-A10B outperforms Qwen3-235B-A22B on several language benchmarks including instruction-following and STEM reasoning, and its visual capabilities exceed those of Qwen3-VL-235B, despite being a newer and architecturally different model.

Qwen3.5 122B A10B

3450°

#llm #qwen #vision #video #reasoning #multilingual

Vision

Runs on Graydient

Run this model

Offers / Ads

Easy Creator (Prism) Web

Unlimited · flat fee

Best for beginners. Describe what you want in a chat and the picture comes back, no learning curve.

PirateDiffusion Telegram

Unlimited · flat fee

Images and video from a chat, with short commands. The most convenient tool for Telegram users, with a web companion.

Pro studio (SpyGlass) Web

Unlimited · flat fee

Best for power users. Full control over models, settings and workflows in a browser studio.

Discord bot (Vector)

Unlimited · flat fee

Best for communities. Add it to your own server and run any workflow from a channel.

Unified Editor Web

Unlimited · flat fee

One screen for every model and workflow: prompts, references, edits and video, built into your Graydient account.

OpenRouter Terminal / API

Pay per token

Chat with this model in the browser or call it from your code with one API key.

Local apps

Requires setup

Set up local programs if your computer has capable hardware.

ModelDuel Web

Pay per use

Generate the same prompt on up to 50 checkpoint/base models at a time.

Rent a GPU on the cloud

Graydient Cloud GPU

Unlimited · flat fee

Flat fee, unlimited use. This model installs with one click.

RunPod Cloud GPU

Charged by the minute

Rent a GPU by the minute and set the model up yourself.

Guides for this model

Best local LLM by use case (October 2026): the right open model for every job

How much VRAM do I actually need for local AI?

Open weights vs open source vs API-only: what you are actually allowed to do

What is a GGUF file? Quantized models explained (Q4, Q8, fp8, NF4)

All guides

Qwen | 262,144 token context | $0.26/M input, $2.08/M output. The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of overall performance, this model is second only to Qwen3.5-397B-A17B. Its text capabilities significantly outperform those of Qwen3-235B-2507, and its visual capabilities surpass those of Qwen3-VL-235B.

Captain's notes

Written by Captain, the house editor

Notes from 2026-10-13

Qwen3.5-122B-A10B is a native vision-language model from Qwen that pairs a 122B sparse mixture-of-experts architecture with a linear attention mechanism, activating only 10B parameters per forward pass. It handles text, images, and video across 201 languages with a 262K native context window. It sits just below the 397B flagship in Qwen's own lineup, making it the practical choice when you want near-top performance without the full inference cost.

Known for

Vision and language in one model, trained with early fusion rather than bolted-on adapters.
Only 10B parameters active per pass despite 122B total — inference is faster and cheaper than the size suggests.
262,144-token native context, extensible further.
Strong instruction-following and reasoning benchmarks, outperforming Qwen3-235B-A22B on several tasks.
201 languages and dialects supported.

Watch out for

Output pricing at $2.08/M is not cheap; long agentic runs with heavy output will add up.
122B total weights means local deployment demands serious hardware — not a laptop model.
Licence terms are not detailed in what Qwen has published here; check the Hugging Face repository before any commercial use.

Best for

Prompts to try

Analyse a complex image

Attach a chart, diagram, or photograph. Describe what you see in detail, identify any patterns or anomalies, and explain what a domain expert would likely conclude from this image.

Hard multi-step reasoning

A factory has three machines. Machine A produces 120 units per hour but breaks down for 15 minutes every 2 hours. Machine B produces 90 units per hour with no downtime. Machine C produces 150 units per hour but requires a 30-minute warmup before each 3-hour run. How many units does the factory produce in a 12-hour shift if all three start simultaneously? Show your working.

Long document Q&A

Paste a long contract, report, or research paper below. Then ask: what are the three most significant obligations or findings, what risks or caveats does the author flag, and is there anything that appears internally inconsistent?

Compare with

Qwen3.7 Flash
API-only model
1,000,000 token context · $0.03/M input, $0.13/M output
Qwen3.8 Max (0902)
API-only model
1,000,000 token context · $2.00/M input, $6.00/M output
Qwen3.8 Omni Flash
API-only model
1,000,000 token context · $0.15/M input, $0.47/M output
Qwen3 VL 32B Instruct
API-only model
131,072 token context · $0.10/M input, $0.42/M output

More text models from qwen

Questions people ask

Can I run Qwen3.5-122B-A10B locally?: Yes, the weights are open and hosted at Qwen/Qwen3.5-122B-A10B on Hugging Face, compatible with Transformers, vLLM, SGLang, and KTransformers. You will need substantial VRAM or a multi-GPU setup given the 122B total parameter count.
What does it cost and what is the context window?: Via API it is priced at $0.26 per million input tokens and $2.08 per million output tokens, with a native context of 262,144 tokens.
How does this compare to Qwen3-235B-A22B?: Qwen3.5-122B-A10B outperforms Qwen3-235B-A22B on several language benchmarks including instruction-following and STEM reasoning, and its visual capabilities exceed those of Qwen3-VL-235B, despite being a newer and architecturally different model.

Captain's verdict
A genuinely capable vision-language model that punches above its active-parameter weight — worth serious consideration if you need multimodal reasoning at scale.

Model card on Hugging Face

Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.

Ranking badge

Updated Oct 22, 2026

Made this model? Show this badge on your page.

Paste it into your Hugging Face card or Civitai description.

Change colors / personalize / get code

Not this creator?

Get your own badge

How this score adds up

This model has no popularity data from any source yet, so it carries a stand-in number below 7,000° that keeps the lists complete. It never ranks above a model with data. The breakdown appears here as soon as a source reports it.

Glossary: the terms used here

Heat score: One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
Floor: The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
Download-equivalents: Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
Log scale: Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
Likes: Thumbs up and likes from every source, worth half a download each on the log scale.
Adoption rate: How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
Measured and estimated: Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
Seeder: Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
AI Horde: A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
Generation sites: Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
OpenRouter tokens: A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
Full model (checkpoint): The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
LoRA and embedding: Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
Family and weights: The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
Age: Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
Family boost: A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
Stand-in score: A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
New! (grace period): A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
Trend: How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
Typical model: The middle of the catalog: half the models with a figure grew faster over the period, half slower.

Similar Models

AI Models for Image, Video & Text Generation

Qwen3.5 122B A10B is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.

More Text / LLM models llm qwen vision video reasoning multilingual long context local

Browse by Model Family