groxaxo

Qwen-AgentWorld-35B-A3B-GPTQ-Pro-Int4

README

License: apache-2.0

Overview

Qwen-AgentWorld-35B-A3B-GPTQ-Pro-Int4 is a GPTQ-quantized checkpoint intended for efficient GPU inference, published by groxaxo. It is intended for open-source evaluation, reproducible experimentation, and compatible local or hosted inference workflows. The wording below is deliberately limited to what can be verified from this repository's metadata and artifacts.

At a glance

Table with columns: Field, Details
Field	Details
Format	GPTQ
Source / base	`Qwen/Qwen-AgentWorld-35B-A3B`
Intended task	`image-text-to-text`
License	`apache-2.0`

What is included

*.safetensors (5 files)
config.json
generation_config.json
tokenizer.json
tokenizer_config.json
chat_template.jinja
quantize_config.json
Additional configuration, tokenizer, processor, or shard files (13 visible artifacts total)

Quick start

vLLM (documented configuration)

bash
vllm serve groxaxo/Qwen-AgentWorld-35B-A3B-GPTQ-Pro-Int4 \
  --quantization gptq_marlin \
  --dtype float16 \
  --trust-remote-code

This command is taken from the repository documentation. Adjust tensor parallelism, context length, and cache settings to match your hardware and vLLM version.

Compatibility and responsible use

Use a runtime that explicitly supports this format, architecture, and modality.
Keep configuration, tokenizer, processor, projection, and weight files from the same revision together.
Review the source model card and license before redistribution or deployment.
Hardware needs depend on parameter count, context length, cache precision, quantization, and concurrency.
Report reproducible issues with the runtime version, hardware, launch command, and a minimal example.

Quantization or conversion changes numerical behavior, memory use, and throughput relative to the source checkpoint; validate quality on your own workload.

Generated outputs may be inaccurate or unsuitable for a given use case. Users are responsible for testing behavior, applying appropriate safeguards, and complying with applicable licenses and laws.

A compact 4-bit GPTQ-Pro quantization of Qwen-AgentWorld-35B-A3B — built for local agent simulation, tool-use reasoning, terminal/world-state prediction, and long-context agent workflows.

This repository contains an INT4 GPTQ-Pro quantized version of Qwen/Qwen-AgentWorld-35B-A3B, preserving the core architecture and behavior of the original language world model while dramatically reducing the weight footprint for practical local serving.

The upstream model is not just another chat model with a tool-use sticker slapped on it. Qwen-AgentWorld is trained as a language world model: given an agent’s action and interaction history, it predicts the next environment observation/state. That makes it especially interesting for agentic workflows where the model needs to reason about what should happen next inside tools, terminals, browsers, operating systems, software projects, and simulated environments.

This quantized build is intended for people who want to actually run the thing, not frame the BF16 checkpoint and admire it from across the room.

What this model is good at

This model is best suited for:

Agentic environment simulation
Tool-call and MCP-style interaction modeling
Terminal state prediction
Software-engineering workflow simulation
Browser / web / OS interaction reasoning
Synthetic trajectory generation for agents
Long-context planning and replay
Local agent research
OpenAI-compatible backend serving

The upstream AgentWorld model covers seven major interaction domains:

Table with columns: Domain, Use case
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

Model details

Table with columns: Field, Value
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

Why this quant exists

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:

Smaller disk and VRAM footprint
Faster local experimentation
OpenAI-compatible serving
Multi-GPU consumer inference
Agent simulation without calling external APIs
A world-model backend for agent training, evaluation, or synthetic rollout generation

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.

Recommended serving: vLLM

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

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Model Details

Model Provider

groxaxo

Model Tree

Base

Qwen/Qwen-AgentWorld-35B-A3B

Quantized

this model

Input Modalities

TextImageVideo

Output Modalities

Text

Supported Functionality