Qwen3 30B A3B Instruct 2507
3007°
Run this model
Offers / Ads
Qwen | 262,144 token context | $0.10/M input, $0.30/M output. Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and agentic tool use. Post-trained on instruction data, it demonstrates competitive performance across reasoning (AIME, ZebraLogic), coding (MultiPL-E, LiveCodeBench), and alignment (IFEval, WritingBench) benchmarks. It outperforms its non-instruct variant on subjective and open-ended tasks while retaining strong factual and coding performance.
Guides for this model
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)
Captain's notes
Notes from 2026-10-13
Qwen3-30B-A3B-Instruct-2507 is a mixture-of-experts model from Qwen with 30.5B total parameters but only 3.3B active per inference, making it punchy relative to its compute cost. This July 2025 update to the non-thinking variant sharpens instruction following, writing quality, and long-context handling across a 262K token window. It suits developers and writers who want frontier-adjacent quality at a fraction of frontier prices.
Known for
- ZebraLogic score of 90.0 beats every model in its comparison table
- Writing benchmarks top the comparison, including Creative Writing and WritingBench
- Only 3.3B parameters active per forward pass despite a 30.5B total parameter count
- Native 256K long-context understanding built into the base architecture
- Open weights available on Hugging Face for local deployment
Watch out for
- Non-thinking mode only — no chain-of-thought reasoning blocks, by design and not configurable
- Aider-Polyglot coding score lags DeepSeek-V3 and Qwen3-235B noticeably; complex multi-file edits may disappoint
- Agent benchmarks (TAU2-Telecom, TAU2-Retail) trail several smaller or cheaper rivals
Prompts to try
Logic puzzle from scratch
Five houses in a row are each painted a different color. The owner of the green house drinks coffee. The person who drinks tea lives next to the person with the fox. The middle house owner drinks milk. The Norwegian lives in the first house. Work out who owns the zebra and who drinks water. Show your reasoning step by step.
Rewrite for clarity
Rewrite the following paragraph so it is clear, direct and suitable for a general audience. Cut any filler, fix any awkward phrasing, and keep all the factual content intact. Paragraph: 'The utilization of advanced methodological frameworks in the context of organizational change management initiatives has been shown to potentially facilitate the achievement of more optimal outcomes in terms of stakeholder alignment and resource allocation efficiency.'
Refactor this function
Refactor this Python function so it handles edge cases cleanly, uses type hints, and includes a short docstring. Explain each change you make and why. def calc(items, disc=0): total = 0; [total := total + i['price'] for i in items]; return total - total * disc
Compare with
- Qwen3.8 Max (0902)API-only model1,000,000 token context · $2.00/M input, $6.00/M output
- Qwen3.7 PlusAPI-only model1,000,000 token context · $0.32/M input, $1.28/M output
- Qwen3.6 PlusAPI-only model1,000,000 token context · $0.33/M input, $1.95/M output
- Qwen3.6 Max PreviewAPI-only model262,144 token context · $1.03/M input, $6.16/M output
More text models from qwen
Questions people ask
- Can I run Qwen3-30B-A3B-Instruct-2507 locally?
- Yes, the weights are open and hosted on Hugging Face at Qwen/Qwen3-30B-A3B-Instruct-2507, so you can download and run it with tools like Ollama or LM Studio.
- What does it cost via API and what is the context window?
- Pricing is $0.10 per million input tokens and $0.30 per million output tokens, with a native context window of 262,144 tokens.
- How does this differ from the original Qwen3-30B-A3B non-thinking model?
- This 2507 update improves instruction following, writing alignment, long-tail multilingual knowledge, and long-context understanding over the base non-thinking variant, while keeping the same MoE architecture and non-thinking-only mode.
Captain's verdictA lean MoE that punches well above its active-parameter count, especially for writing and logical reasoning, at a price that is hard to argue with.
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.
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.
Qwen3 30B A3B 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.
Browse by Model Family
Text / LLM Models
434
Anima Models
528
Chroma Models
19
Fibo Models
2
Flux Models
1,496
Flux 2 / Klein Models
1,239
Flux 3 Models
3
Moss Models
3
Iris Models
1
MiniMax H3 Models
364
Hunyuan Models
204
Ideogram Models
20
Krea2 Models
717
Qwen Models
20
Qwen2 Models
47
Ltx2 Models
153