GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
groxaxo
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
groxaxo
Model Tree
Qwen/Qwen-AgentWorld-35B-A3B
Input Modalities
Output Modalities
Supported Functionality
This model is best suited for:
The upstream AgentWorld model covers seven major interaction domains:
| Domain | Use case |
|---|---|
| MCP / Tool calling | Predicting tool results and interaction flow |
| Search | Simulating search-based information environments |
| Terminal | Predicting shell command outputs and filesystem-like state |
| SWE | Software-engineering task environments |
| Android | Mobile GUI interaction simulation |
| Web | Browser and website interaction simulation |
| OS | Desktop / operating-system style workflows |
| Field | Value |
|---|---|
| Base model | Qwen/Qwen-AgentWorld-35B-A3B |
| Quantized model | groxaxo/Qwen-AgentWorld-35B-A3B-GPTQ-Pro-Int4 |
| Architecture | Qwen3.5 MoE / Language World Model |
| Total parameters | 35B |
| Active parameters | ~3B active per token |
| Quantization | GPTQ-Pro INT4 |
| Format | Safetensors |
| Context length |
The original BF16 checkpoint is powerful, but heavy. This GPTQ-Pro INT4 build is aimed at practical deployment where you want the AgentWorld behavior without needing a datacenter-class inference box.
Use this when you want:
Quantization is not magic. INT4 can affect fidelity, especially for very long-context workloads. For serious benchmark or production use, compare against the BF16 upstream model on your own tasks.
Use a recent vLLM build. Qwen3.5 MoE support is new enough that old wheels may fail or silently behave like garbage. Delightful hobby, this one.
bash
pip install -U vllm
| Up to 262,144 tokens, depending on serving stack and VRAM |
| License | Apache-2.0, following upstream |