Qwen3.5 27B
5296°
Run this model
Offers / Ads
Qwen | 262,144 token context | $0.26/M input, $2.60/M output. The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of the Qwen3.5-122B-A10B.
Guides for this model
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?
Best local LLM by use case (October 2026): the right open model for every job
What is a GGUF file? Quantized models explained (Q4, Q8, fp8, NF4)
Captain's notes
Notes from 2026-10-13
Qwen3.5-27B is a 27-billion-parameter vision-language model from Qwen with a hybrid linear-attention architecture that keeps inference fast without sacrificing much capability. Its benchmark scores sit close to Qwen's own 122B MoE model, which is a notable gap to close at this size. It suits developers who want strong reasoning, coding, and multimodal ability in a model they can run locally or call cheaply via API.
Known for
- Linear attention hybrid cuts latency while matching much larger models on most benchmarks.
- Handles text, images, and video natively through early-fusion multimodal training.
- Strong instruction-following: leads the comparison set on IFEval and IFBench.
- 201 languages and dialects supported out of the box.
- 262K native context, extensible to over one million tokens.
Watch out for
- Output tokens cost ten times the input rate ($2.60/M out vs $0.26/M in); heavy generation adds up.
- At 27B parameters, local use demands significant VRAM — plan accordingly before downloading.
- The linear attention architecture is non-standard; some inference stacks may not support it yet.
Prompts to try
Debug a tricky async bug
Here is a Python async function that occasionally deadlocks under load. Walk through what is happening, explain the root cause, and rewrite it so the deadlock cannot occur. Then add a brief test that would have caught this.
```python
async def fetch_all(urls):
results = []
lock = asyncio.Lock()
async def fetch(url):
async with lock:
async with aiohttp.ClientSession() as session:
async with session.get(url) as r:
results.append(await r.text())
await asyncio.gather(*[fetch(u) for u in urls])
return results
```
Plan a complex multi-step project
I need to migrate a monolithic Rails app (about 200k lines, PostgreSQL, no test suite) to a set of independent services over 18 months without taking the product offline. The team is six engineers. Lay out a phased plan, flag the three highest-risk decisions I will face, and suggest how to sequence them to keep risk manageable.
Describe and critique a diagram
I am attaching a system architecture diagram. Identify every component shown, trace the data flow from user request to response, and point out any single points of failure or bottlenecks you can see. If anything looks unusual or potentially misconfigured, flag it.
Compare with
- Qwen3.7 FlashAPI-only model1,000,000 token context · $0.03/M input, $0.13/M output
- Qwen3.8 Max (0902)API-only model1,000,000 token context · $2.00/M input, $6.00/M output
- Qwen3.8 Omni FlashAPI-only model1,000,000 token context · $0.15/M input, $0.47/M output
- Qwen3.5 Plus 2026-02-15API-only model1,000,000 token context · $0.26/M input, $1.56/M output
More text models from qwen
Questions people ask
- Can I run Qwen3.5-27B locally?
- Yes, the weights are open and hosted on Hugging Face at Qwen/Qwen3.5-27B. It is compatible with Hugging Face Transformers, vLLM, SGLang, and KTransformers, among others.
- What does Qwen3.5-27B cost and what is the context window?
- Via API it is priced at $0.26 per million input tokens and $2.60 per million output tokens, with a native context of 262,144 tokens that the maker says can be extended beyond one million.
- How does Qwen3.5-27B compare to Qwen3.5-122B-A10B?
- Qwen describes overall capability as comparable to the 122B MoE model; the benchmarks show the 27B slightly behind on some reasoning tasks but ahead on instruction-following metrics like IFEval.
Captain's verdictA rare dense model that punches well above its weight class — worth serious consideration if you need local multimodal reasoning without a massive parameter bill.
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.
Qwen3.5 27B 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