Can I run Qwen3.6-35B-A3B locally?

Yes — the weights are open under the Apache 2.0 licence and are available on Hugging Face, compatible with Transformers, vLLM, SGLang and KTransformers. Because only 3B parameters are active per token, memory requirements are lower than the 35B total parameter count suggests; check a VRAM guide before downloading.

What does it cost and what is the context window?

Via API it is $0.10 per million input tokens and $0.95 per million output tokens, with a native context of 262,144 tokens — extensible to around 1 million tokens via YaRN.

How does this compare to Qwen3.5-35B-A3B?

Qwen3.6 is the direct successor, built on community feedback, with the main gains in agentic coding benchmarks and a new option to preserve reasoning traces across multi-turn conversations; general knowledge scores are broadly similar.

▲

121%

this week

Qwen3.6 35B A3B

8682°

#llm #qwen #vision #video #reasoning #coding

This week

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 | $0.15/M input, $1.00/M output. Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated DeltaNet linear attention with standard gated attention layers, enabling efficient inference at a fraction of the compute cost. The model supports a 262K token native context window (extensible to 1M via YaRN) and accepts text, image, and video inputs. It includes integrated thinking mode with reasoning traces preserved across multi-turn conversations, function calling, and structured output. Released under the Apache 2.0 license.

Guides for this model

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

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

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?

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

Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud built on a hybrid sparse mixture-of-experts architecture: 35 billion total parameters but only 3 billion active per token, which keeps inference costs low. Its headline improvement over its predecessor is agentic coding, particularly frontend workflows and repository-level tasks. If you need a capable coder and agent that you can run locally or hit cheaply via API, this is worth a serious look.

Known for

Agentic coding: strong on frontend workflows and repository-level reasoning
Only 3B parameters active per token, so inference is fast and cheap
Native 262K context window, extensible to roughly 1M via YaRN
Accepts text, image and video inputs with integrated thinking mode
Reasoning traces preserved across multi-turn conversations

Watch out for

Output tokens cost nearly 10× input tokens at $0.95/M — long agentic runs add up.
The hybrid linear-attention architecture is less battle-tested than standard transformers; some inference stacks may lag on support.
Vision and video input quality is not independently benchmarked in the published results.

Best for

Prompts to try

Refactor a messy codebase

I have a React frontend with all state managed in a single 800-line App.js file. There are no components, no custom hooks, and props are drilled four levels deep. Analyse the structure, identify the three most damaging problems, then produce a concrete refactoring plan with file names and the order of changes I should make.

Multi-step agent plan

You are an agent with access to bash and file-edit tools. A user's Python project fails its CI pipeline because of three flaky tests that depend on a real network call to an external API. Walk through how you would locate the tests, design a mocking strategy, implement the fix, and verify it without touching the production code path.

Hard reasoning puzzle

Five engineers each own a different programming language, drink a different beverage, and work in a different timezone. The Rust engineer drinks espresso. The engineer in UTC+9 owns Python. The TypeScript engineer is immediately to the left of the coffee drinker. The Go engineer works in UTC-5. Who drinks tea, and what language do they use? Show your reasoning step by step.

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
Qwen3.5 Plus 2026-02-15
API-only model
1,000,000 token context · $0.26/M input, $1.56/M output

More text models from qwen

Questions people ask

Can I run Qwen3.6-35B-A3B locally?: Yes — the weights are open under the Apache 2.0 licence and are available on Hugging Face, compatible with Transformers, vLLM, SGLang and KTransformers. Because only 3B parameters are active per token, memory requirements are lower than the 35B total parameter count suggests; check a VRAM guide before downloading.
What does it cost and what is the context window?: Via API it is $0.10 per million input tokens and $0.95 per million output tokens, with a native context of 262,144 tokens — extensible to around 1 million tokens via YaRN.
How does this compare to Qwen3.5-35B-A3B?: Qwen3.6 is the direct successor, built on community feedback, with the main gains in agentic coding benchmarks and a new option to preserve reasoning traces across multi-turn conversations; general knowledge scores are broadly similar.

Captain's verdict
A rare combination: open weights, multimodal input, long context and genuinely competitive agentic coding at a price that does not sting.

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

Also ranked: Silver · Hottest this week · #114 Hottest AI model · #48 Hottest Text / LLM model · #48 Hottest Text / LLM text model

Not this creator?

Get your own badge

Qwen3.6 35B A3B Popularity Trend

Heat score since 27 Apr 2026

Heat score

8,682°

This week

▲

121%

8,578° then, 8,682° now

This month

n/a

Wasn't released/tracked

Past year

n/a

Wasn't released/tracked

7,000°

Floor

The scale runs from 0° to 9,999°. Everything below 7,000° is kept for models no source reports on yet, which carry a stand-in number there so lists stay complete. 7,000° is where measured data begins: a model with real data but almost no downloads sits at the floor, and the measurements fill the degrees above it. The floor says nothing about the model; only the degrees above it do, and they are what separates one model from another.

+1,365°

OpenRouter tokens

355,046,263,575 tokens this model processed through OpenRouter in the last 30 days, prompts and answers together. Every 10,000,000 tokens count as one download in the download term, 35,504 in all; the last day's tokens join the adoption rate. Source: OpenRouter (openrouter.ai/rankings).

+317°

Adoption rate

About 16,735 downloads a day, measured between two readings of the sources, never guessed from a lifetime average. Speed weighs a quarter of the download term, so a fresh surge shows without letting a one-day spike outrank years of use.

Show detailed breakdown

Every number on this site can be checked. This model's heat score is 8,682°, and here it is built one ingredient at a time, with the running total after each: the floor, the degrees each source adds, the bonus for the kind of model and what the age of its weights takes away. The colors are the bands of the chart above. The glossary at the end defines every term.

1
Start at the floor.
Why 7,000° and not zero: the scale runs from 0° to 9,999°, and the part below 7,000° is reserved for models no source reports on yet, which carry a stand-in number there so the lists stay complete and never outrank a model with data. 7,000° is where measured data begins. A model with real data but almost no downloads sits here; everything that follows is measurement, and the room above the floor holds ten tenfold steps in downloads at 300° each. The floor is the same for every model, so it decides nothing; the degrees above it do.
7,000°
running total
2
Add the downloads.
35,504 download-equivalents in all, from OpenRouter tokens. Ten times the downloads adds the same 300°, so size matters but never runs away with the score.
+1,365°
8,365°
running total
3
Add the adoption rate.
About 16,735 downloads a day right now, measured between two readings, at a quarter of the weight.
+317°
8,682°
running total
=
The heat score.
Where this model stands on every list of this site. Nothing else adjusts it.
8,682°

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.

How this model's popularity has moved against the rest of the catalog: its growth in downloads, likes and usage over each period, measured against the typical model's growth over the same period, with its heat score at the time. Above the typical growth reads as a rise, below it as a fall. The past is reconstructed from today's totals, the model's first day and its measured download speed where two readings exist; a model that did not exist at the start of a period shows n/a.

Similar Models

AI Models for Image, Video & Text Generation

Qwen3.6 35B A3B 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 coding agents local

Browse by Model Family