Released 2026-06-24 · world model

Deployment evidence

Alibaba Qwen · 35B total · 3B active · 256K tokens

Official weights Model documentation

PrecisionBF16Serving pathsSGLang, vLLM

Best-fit scenarios

A language world model for simulating MCP, Search, Terminal, SWE, Android, Web and OS agent environments.

Not recommended

General-purpose chat replacement
Treating simulated success as proof of real-environment reliability

Agent environment simulation

Vendor-stated

The model predicts environment transitions across seven unified domains.

Capability source

Synthetic trajectories and perturbation tests

Vendor-stated

Official materials highlight controllable simulation and fictional-world construction.

Capability source

Agent regression evaluation

ChinaAPI inference

Useful as a simulator component, not as a drop-in customer chatbot.

Official launch / minimum

Evidence C

Official tp4 launch

Official SGLang and vLLM examples use tensor parallel size 4. Primary recipe

200-person team

Evidence E

Not a seat based service

Size by simulation jobs and trajectory length, not employee seats.

Commercial API

Evidence E

Specialized service

Expose behind a task-specific simulator contract; do not market it as a normal chat-completions quality substitute.

Commercial-use check

Apache-2.0

MaaS / hosted service: No model-specific MaaS restriction identified in Apache-2.0.

Attribution: Provide the license and notices, preserve attribution notices, and mark modified files.

Read the primary license text

Known limitations and open questions

World-model outputs are simulations
The 35B release covers seven named domains, not arbitrary physical environments

Qwen-AgentWorld-35B-A3B: self-hosting hardware, scenarios and commercial license