Can I run Qwen3-235B-A22B-Instruct-2507 locally?

Yes, the weights are open and available on Hugging Face at Qwen/Qwen3-235B-A22B-Instruct-2507. At 235B total parameters you will need substantial GPU memory — check the model card's hardware requirements before committing to a download.

What does it cost via API, and how long is the context?

Pricing is $0.09 per million input tokens and $0.55 per million output tokens. The native context window is 262,144 tokens.

How is this different from the original Qwen3-235B-A22B non-thinking model?

This 2507 update brings meaningful gains in knowledge coverage, long-context understanding, math reasoning and alignment with open-ended tasks over the base non-thinking variant, while keeping the same architecture and active parameter count.

Qwen3 235B A22B Instruct 2507

4361°

#llm #qwen #reasoning #math #coding #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 | $0.09/M input, $0.55/M output. Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following, logical reasoning, math, code, and tool usage. The model supports a native 262K context length and does not implement "thinking mode" ( blocks). Compared to its base variant, this version delivers significant gains in knowledge coverage, long-context reasoning, coding benchmarks, and alignment with open-ended tasks. It is particularly strong on multilingual understanding, math reasoning (e.g., AIME, HMMT), and alignment evaluations like Arena-Hard and WritingBench.

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?

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

Qwen3-235B-A22B-Instruct-2507 is Alibaba's updated non-thinking-mode release of their 235B mixture-of-experts model, with 22B parameters active per forward pass. It trades the chain-of-thought reasoning blocks of the thinking variant for faster, cleaner output while still posting strong numbers on math, coding, knowledge and multilingual benchmarks. Open weights and a 262K native context make it a serious option if you want frontier-class capability without a closed API.

Known for

Math reasoning: leads the benchmark table on AIME25 and HMMT25 among listed models.
Factual knowledge: notably strong on SimpleQA and CSimpleQA versus its direct peers.
Native 262K context window with reported extendability well beyond that.
Multilingual instruction following across a wide range of languages.
Tool use and function calling competitive with larger closed models.

Watch out for

No thinking mode: this version does not produce reasoning traces; use the base thinking variant if you need that.
235B total parameters means local deployment requires serious hardware — check VRAM requirements before downloading.
Qwen publishes the weights but check the licence terms on Hugging Face before any commercial use.

Best for

Prompts to try

Hard competition math

Solve this problem step by step: A sequence is defined by a₁ = 1 and aₙ₊₁ = aₙ + 1/aₙ for n ≥ 1. Prove that a₂₀₀ > 20, and find the smallest integer N such that aₙ > 20 for all n ≥ N.

Multilingual contract clause

A supplier contract contains this clause: 'Le fournisseur garantit la livraison dans un délai de 30 jours ouvrables à compter de la réception de la commande, sous peine d'une pénalité de 0,5 % par jour de retard.' Explain the legal and commercial implications in English, then rewrite the clause to cap total penalties at 10% of contract value.

Long-document reasoning

I will paste the full text of a research paper below. After reading it, identify the three strongest claims the authors make, the evidence they provide for each, any methodological weaknesses a peer reviewer would flag, and one follow-on experiment that would meaningfully strengthen the weakest claim. Paste your paper now and I will begin.

Compare with

Qwen3.8 Max (0902)
API-only model
1,000,000 token context · $2.00/M input, $6.00/M output
Qwen3 30B A3B Thinking 2507
API-only model
81,920 token context · $0.20/M input, $2.40/M output
Qwen3.5 Plus 2026-02-15
API-only model
1,000,000 token context · $0.26/M input, $1.56/M output
Qwen3.7 Plus
API-only model
1,000,000 token context · $0.32/M input, $1.28/M output

More text models from qwen

Questions people ask

Can I run Qwen3-235B-A22B-Instruct-2507 locally?: Yes, the weights are open and available on Hugging Face at Qwen/Qwen3-235B-A22B-Instruct-2507. At 235B total parameters you will need substantial GPU memory — check the model card's hardware requirements before committing to a download.
What does it cost via API, and how long is the context?: Pricing is $0.09 per million input tokens and $0.55 per million output tokens. The native context window is 262,144 tokens.
How is this different from the original Qwen3-235B-A22B non-thinking model?: This 2507 update brings meaningful gains in knowledge coverage, long-context understanding, math reasoning and alignment with open-ended tasks over the base non-thinking variant, while keeping the same architecture and active parameter count.

Captain's verdict
A rare case where open weights, a 262K context and genuinely competitive math and knowledge scores arrive in the same model.

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

NVIDIA Nemotron 3 Super 120B A12B

AI Models for Image, Video & Text Generation

Qwen3 235B A22B Instruct 2507 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 reasoning math coding multilingual long context

Browse by Model Family