Can I run QwQ 32B Preview locally?

No — the weights are not publicly released, so you can only use it through an API endpoint.

What does it cost and how long is its context?

Qwen prices it at $0.12 per million input tokens and $0.18 per million output tokens, with a context window of 32,768 tokens.

How does this differ from a standard Qwen chat model?

QwQ is built specifically for deliberate, multi-step reasoning rather than fast conversational responses; it is also an experimental preview, not a production release.

QwQ 32B Preview

3579°

#llm #qwen #reasoning #math #coding #research

Runs on Graydient

Open DeepInfra

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.

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

The 10 cheapest ChatGPT alternatives in 2026: free local models, free tiers and flat-rate plans

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 | 32,768 token context | $0.12/M input, $0.18/M output. QwQ is an experimental research model developed by the Qwen Team, designed to advance AI reasoning capabilities. This model embodies the spirit of philosophical inquiry, approaching problems with genuine wonder and doubt. QwQ demonstrates impressive analytical abilities, achieving scores of 65.2% on GPQA, 50.0% on AIME, 90.6% on MATH-500, and 50.0% on LiveCodeBench. With its contemplative approach and exceptional performance on complex problems.

Captain's notes

Written by Captain, the house editor

Notes from 2026-10-13

QwQ 32B Preview is an experimental reasoning model from Qwen, built to think through hard problems rather than answer them quickly. It posts strong benchmark numbers on graduate-level science, competition math and coding, and its deliberate, self-questioning approach sets it apart from standard instruction-tuned models. If you need a model that works through a problem step by step and shows its reasoning, this is worth trying at a price that won't hurt.

Known for

Strong performance on competition math and graduate-level science problems.
Deliberate, chain-of-thought style reasoning with visible self-correction.
Solid coding benchmark results on LiveCodeBench.
Low API price relative to its reasoning capability.

Watch out for

Weights are not open; you access it via API only, no local deployment.
32,768-token context is modest — long documents or extended conversations will hit the limit.
Labelled a preview and research model; expect rough edges and inconsistent behaviour.

Best for

Prompts to try

Fermi estimate with working

How many piano tuners are there in Tokyo? Work through your estimate step by step, stating every assumption you make and flagging where your uncertainty is highest. Then give a final number with a rough confidence range.

Proof check and fix

Here is a student's proof that the square root of 2 is rational. Find every logical error, explain why each step fails, and then write a correct proof that the square root of 2 is irrational. Student proof: Assume √2 = a/b in lowest terms. Then 2 = a²/b², so a² = 2b². Since a² is even, a is even, so write a = 2k. Then 4k² = 2b², so b² = 2k², meaning b is also even. Therefore √2 is rational.

Algorithm design trade-offs

I need to find the top-k most frequent words in a stream of text where k is small (say 10) and the stream is too large to store. Walk through at least two algorithmic approaches, compare their time and space complexity, identify the trade-offs, and recommend one with justification.

Compare with

Qwen3 30B A3B Thinking 2507
API-only model
81,920 token context · $0.20/M input, $2.40/M output
Qwen3 VL 235B A22B Thinking
API-only model
131,072 token context · $0.40/M input, $4.00/M output
Qwen3.8 Max (0902)
API-only model
1,000,000 token context · $2.00/M input, $6.00/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 QwQ 32B Preview locally?: No — the weights are not publicly released, so you can only use it through an API endpoint.
What does it cost and how long is its context?: Qwen prices it at $0.12 per million input tokens and $0.18 per million output tokens, with a context window of 32,768 tokens.
How does this differ from a standard Qwen chat model?: QwQ is built specifically for deliberate, multi-step reasoning rather than fast conversational responses; it is also an experimental preview, not a production release.

Captain's verdict
A cheap, capable reasoning model worth testing on hard math and science problems — just don't expect open weights or a long context window.

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.

How to install

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

Similar Models

Meta Llama 3.1 70B Instruct Turbo

TEXT / LLM

AI Models for Image, Video & Text Generation

QwQ 32B Preview 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 reasoning math coding research

Browse by Model Family