Qwen3.6-27B

Qwen3.6-27B

Alibaba
+
+

Related Products

  • Evertune
    1 Rating
    Visit Website
  • Epicor Kinetic
    533 Ratings
    Visit Website
  • LM-Kit.NET
    29 Ratings
    Visit Website
  • Sogolytics
    869 Ratings
    Visit Website
  • KonstructIQ
    7 Ratings
    Visit Website
  • AthenaHQ
    50 Ratings
    Visit Website
  • HubSpot AEO
    151 Ratings
    Visit Website
  • DonorPerfect Fundraising Growth Platform
    2,401 Ratings
    Visit Website
  • iBabs
    79 Ratings
    Visit Website
  • SBS Asset Finance
    3 Ratings
    Visit Website

About

Perplexity Decider is a 27B decision model fine-tuned from Qwen3.8-27B for structured classification and multimodal decision tasks. Rather than generating unrestricted text, it takes an input state and a typed decision schema, then returns the selected result together with calibrated probabilities. The model supports choice decisions for selecting among predefined categories and noul decisions for estimating the probability of a yes-or-no condition. It can also accept images alongside text, allowing applications to make decisions from screenshots or other visual inputs. Example workflows include routing a support request to billing, technical support, or sales, and estimating whether a message expresses urgency. Perplexity reports an overall accuracy of 85.71% across 11 benchmarks, including FinancialPhraseBank, RAGTruth, JudgeBench, TabFact, ContractNLI, Circa, Belebele, and TruthfulQA binary.

About

Qwen3.6-27B is a dense, open source multimodal language model in the Qwen3.6 series, designed to deliver flagship-level performance in coding, reasoning, and agent-based workflows while maintaining a relatively efficient parameter size of 27 billion. It is positioned as a high-performance general model that “punches above its weight,” achieving results competitive with or superior to significantly larger models on key benchmarks, particularly in agentic coding tasks. It supports both thinking and non-thinking modes, allowing it to dynamically balance deep reasoning with fast responses depending on the task, and integrates capabilities across text and multimodal inputs such as images and video. Built as part of the Qwen3.6 family, the model emphasizes real-world usability, stability, and developer productivity, incorporating improvements driven by community feedback and practical deployment needs.

Platforms Supported

Windows Not Supported
Mac Not Supported
Linux Not Supported
Cloud Supported
On-Premises Not Supported
iPhone Not Supported
iPad Not Supported
Android Not Supported
Chromebook Not Supported

Platforms Supported

Windows Supported
Mac Supported
Linux Not Supported
Cloud Supported
On-Premises Not Supported
iPhone Supported
iPad Supported
Android Supported
Chromebook Not Supported

Audience

Teams and developers wanting to self-host structured classification, routing, and multimodal decision workflows with calibrated probabilities

Audience

Developers and AI engineers who need a powerful, open source model capable of advanced coding, reasoning, and agent workflows

Support

Phone Support Not Supported
24/7 Live Support Not Supported
Online Supported

Support

Phone Support Not Supported
24/7 Live Support Not Supported
Online Supported

API

Offers API Supported

API

Offers API Supported

Screenshots and Videos

Screenshots and Videos

Pricing

Free
Free Version Supported
Free Trial Not Supported

Pricing

Free
Free Version Supported
Free Trial Not Supported

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

Reviews/Ratings

Overall 5.0 / 5
features 4.0 / 5

Pros & Cons from Real Users

Pros

  • Qwen3.6-27B is exciting because it packs a lot of capability into a model size that still feels realistic for serious builders. It is open-weight, dense, multimodal, and clearly tuned for coding-heavy agent workflows. The agentic coding focus is the biggest win. Qwen specifically calls out integration with coding assistants like OpenClaw, Claude Code, and Qwen Code, which makes it feel useful for real development workflows instead of just benchmark screenshots. I also like the long-context support. For coding agents, repo analysis, technical docs, visual debugging, and multi-step reasoning, having more room for context makes a real difference.

Cons

  • It is still a 27B model, so local use is not effortless. You still need the right hardware, quantization, serving setup, and patience if you want good speed.

Training

Documentation Supported
Webinars Not Supported
Live Online Not Supported
In Person Not Supported

Training

Documentation Supported
Webinars Not Supported
Live Online Not Supported
In Person Not Supported

Company Information

Perplexity
Founded: 2022
United States
huggingface.co/perplexity-ai/pplx-decider-v1-27b

Company Information

Alibaba
Founded: 1999
China
qwen.ai/blog

Alternatives

Clef-flash

Clef-flash

Cloudflare

Alternatives

Clef

Clef

Cloudflare
Bonsai 27B

Bonsai 27B

PrismML
Jev

Jev

TypeSafe AI
Qwen3.5

Qwen3.5

Alibaba
Solar Decide

Solar Decide

Upstage
Qwen3.6

Qwen3.6

Alibaba

Categories

AI Decision Models Supported

Categories

AI Coding Models Supported
AI Models Supported
AI Vision Models Supported

Integrations

Alibaba Cloud Model Studio Not Supported
Cheaper Inference Not Supported
Hugging Face Not Supported
ModelScope Not Supported
Ollama Not Supported
OpenClaw Not Supported
Perplexity Decisions API Supported
Python Not Supported
Qwen Not Supported
Qwen Studio Not Supported
Qwen3.6 Not Supported
Qwen3.8-27B Supported

Integrations

Alibaba Cloud Model Studio Supported
Cheaper Inference Supported
Hugging Face Supported
ModelScope Supported
Ollama Supported
OpenClaw Supported
Perplexity Decisions API Not Supported
Python Supported
Qwen Supported
Qwen Studio Supported
Qwen3.6 Supported
Qwen3.8-27B Not Supported
Claim Perplexity Decider and update features and information
Claim Perplexity Decider and update features and information
Claim Qwen3.6-27B and update features and information
Claim Qwen3.6-27B and update features and information