Can I run Qwen3.5-9B locally?

Yes, the weights are open and published on Hugging Face under the repository Qwen/Qwen3.5-9B. The model is compatible with Hugging Face Transformers, vLLM, SGLang, and KTransformers, so standard local setups apply.

What does Qwen3.5-9B cost and what is its context window?

Via API it is priced at $0.10 per million input tokens and $0.15 per million output tokens. The native context window is 262,144 tokens, with the architecture supporting extension beyond one million tokens.

How does Qwen3.5-9B differ from Qwen3 and Qwen3-VL?

Qwen3.5 replaces the separate language and vision-language model lines with a single unified architecture using early fusion, which Qwen says achieves parity with Qwen3 on language tasks while outperforming Qwen3-VL on visual understanding benchmarks.

Qwen3.5 9B

6123°

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

Run this model

Offers / Ads

OpenRouter Terminal / API

Pay per token

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

Qwen | 262,144 token context | $0.10/M input, $0.15/M output. Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design with early fusion of multimodal tokens, allowing the model to process and reason across text and images within the same context.

Guides for this model

How to Install Ollama and Run a Local AI (Windows, Mac, Linux)

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

Ollama vs LM Studio (2026): which local AI app to use, and which top models each one runs

How much VRAM do I actually need for local AI?

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

All guides

Captain's notes

Written by Captain, the house editor

Notes from 2026-10-13

Qwen3.5-9B is a 9-billion-parameter multimodal model from Qwen that handles text and images within a single unified architecture, using early fusion rather than bolting vision on as an afterthought. Its hybrid Gated Delta Network design is built for throughput, and the 262K native context is unusually long for a model this size. At a tenth of a cent per thousand input tokens with open weights, it suits developers who want a capable vision-language model they can run locally or call cheaply via API.

Known for

Unified vision-language reasoning with early-fusion multimodal tokens
262K native context, extensible further, in a 9B-parameter model
Hybrid Gated Delta Network architecture tuned for low-latency inference
201 languages and dialects supported out of the box
Open weights, compatible with vLLM, SGLang, and Hugging Face Transformers

Watch out for

Vision and video capability is stated in the architecture; real-world multimodal quality is not independently verified here.
Benchmark comparisons in the model card are against Qwen's own family; third-party evals are sparse at this stage.
Licence terms for commercial use are not detailed in what Qwen has published on this page.

Best for

Prompts to try

Multimodal image analysis

Attach a screenshot of a chart or diagram. Describe what it shows, identify any trends or anomalies, and list three questions a data analyst would ask before drawing conclusions from it.

Long-document reasoning

Here is a long technical document. Read it carefully, then: (1) summarise the core argument in three sentences, (2) identify any claims that lack supporting evidence, and (3) suggest two follow-up questions the author should address.

Multilingual code review

Review the following Python function for correctness, edge cases, and performance. Then rewrite the docstring in both English and Mandarin Chinese, keeping the technical meaning exact.

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 Qwen3.5-9B locally?: Yes, the weights are open and published on Hugging Face under the repository Qwen/Qwen3.5-9B. The model is compatible with Hugging Face Transformers, vLLM, SGLang, and KTransformers, so standard local setups apply.
What does Qwen3.5-9B cost and what is its context window?: Via API it is priced at $0.10 per million input tokens and $0.15 per million output tokens. The native context window is 262,144 tokens, with the architecture supporting extension beyond one million tokens.
How does Qwen3.5-9B differ from Qwen3 and Qwen3-VL?: Qwen3.5 replaces the separate language and vision-language model lines with a single unified architecture using early fusion, which Qwen says achieves parity with Qwen3 on language tasks while outperforming Qwen3-VL on visual understanding benchmarks.

Captain's verdict
A genuinely multimodal 9B model at budget API prices with open weights — worth a look before reaching for something three times the size.

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

GPT 5.6 Sol

TEXT / LLM

Qwen3 235B A22B Thinking 2507

TEXT / LLM

Mistral Small 3.2 24B

TEXT / LLM

DeepSeek V3.2

TEXT / LLM

AI Models for Image, Video & Text Generation

Qwen3.5 9B 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 and check its heat score to see how it is trending.

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

Browse by Model Family