Models/Qwen AgentWorld 35B A3B

Text / Qwen

Qwen AgentWorld 35B A3B

Qwen-AgentWorld-35B-A3B is an Apache-2.0 licensed text-generation language world model from the Qwen repository. It is a causal language model based on Qwen/Qwen3.5-35B-A3B-Base, trained through CPT, SFT, and RL stages for agentic environment simulation. The model predicts the next environment state given an agent's action and interaction history, covering seven agent interaction domains: MCP (tool calling), Search, Terminal, SWE, Android, Web, and OS. It has 35B total parameters with 3B activated, a context length of 262,144 tokens, and is compatible with Hugging Face Transformers, vLLM, and SGLang.

EstimatedRepository opened Jun 22, 2026Source checked 9/24/2026Version: 60d2b043

LOCALRENTED GPUOPEN WEIGHTS

Freshness 58 out of 100. Repository age: 140 days old, Jun 22, 2026. Measures age, not quality.

Popularity 57 out of 100. 10,200 downloads in 30 days; 746 lifetime likes. Checked Nov 8, 2026. Measures adoption, not quality.

What do these scores mean?

Two ways to compare models. Neither score measures answer quality, benchmark performance, or whether a model fits your machine.

Freshness · release age

A new release starts at 100. The score halves every 180 days: 100 × 2^(−age in days / 180). When the release date is unavailable, a repository date is a fallback—not proof of when the model was released. Missing dates stay unscored.

Check the date source

Popularity · adoption

Downloads over the past 30 days carry 80% of the score; lifetime likes carry 20%. Both use a logarithmic scale, capped at 10 million downloads and 100,000 likes. If likes are unavailable, downloads carry all the weight. Missing download statistics stay unscored.

round(80 × min(1, log10(1 + downloads) / 7) + 20 × min(1, log10(1 + likes) / 5))

Check the statistics source

Scores as of Nov 9, 2026. Statistics checked Nov 8, 2026. Statistics are marked for refresh after 72 hours.Full scoring method

At a glance

Parameters: 34.66B
Architecture: qwen3_5_moe
License: apache-2.0
Disk space: 64.6 GB
Software: SGLang, vLLM, Transformers

View the model source

MY HARDWARE

Will it run on your machine?

Save your machine to see a personalized rating and its reasoning.

Add my hardware

Best for

Simulating agentic environments by predicting next environment states from agent actions and interaction history
Serving as a language world model for MCP tool-calling environments
Simulating Search, Terminal, SWE, Android, Web, and OS interaction domains
Supporting zero-shot generalization experiments in out-of-domain environments
Acting as a warm-up foundation for multi-turn, tool-calling agentic tasks

Tradeoffs

The supplied source does not specify hardware requirements or performance benchmarks for deployment
No information is provided about license compatibility, licensing restrictions, or commercial-use terms beyond the stated Apache-2.0 license
The source states the model is not trained on outputs from external API services, which may limit behavior involving such services
The supplied performance table is incomplete; no full benchmark results are available to assess real-world capabilities
The source does not include testing claims or independent validation; no claims about actual performance or reliability are made here

Ways to run it

SGLang · Linux

Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.

python -m sglang.launch_server  --model-path Qwen/Qwen-AgentWorld-35B-A3B  --port 8000  --tp-size 4  --context-length 262144  --reasoning-parser qwen3

Official instructions

vLLM · Linux

Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.

vllm serve Qwen/Qwen-AgentWorld-35B-A3B  --port 8000  --tensor-parallel-size 4  --max-model-len 262144  --reasoning-parser qwen3  --language-model-only  --trust-remote-code

Official instructions

Transformers · See official guide

Repository-specific command in publisher documentation; confirm dependencies and hardware in the source.

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Qwen/Qwen-AgentWorld-35B-A3B"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto",
)

messages = [
    {
        "role": "system",
        "content": "You are a language world model simulating a Linux terminal environment. "
                   "Given the user's command, predict the terminal output."
    },
    {
        "role": "user",
        "content": "Action: execute_bash\nCommand: ls -la /home/user/project/"
    }
]

text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer([text], return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=2048, temperature=0.6)
response = tokenizer.decode(outputs[0][inputs.input_ids.shape[-1]:], skip_special_tokens=True)
print(response)

Official instructions

Explore its uses

SAFETENSORSTEXT-GENERATION

Keep exploring

Text

Prism ML

Bonsai 2 · 27B

A compressed 27B-class reasoning model with publisher-provided GGUF packs and a dedicated llama.cpp fork for CUDA, Metal, and CPU.

Freshness 82 out of 100. Release age: 53 days old, Sep 17, 2026. Measures age, not quality.

MODEL SIZE27.36B

LOCALRENTED GPU

Released Sep 17, 2026

Text

DeepSeek

DeepSeek V4.1 Flash

An open-weight model for reasoning, coding, agents, and image understanding. DeepSeek V4.1 Flash combines a 552B backbone with sparse activation and up to one million tokens of context. Choose the original checkpoint or a community uncensored variant below.

Freshness 79 out of 100. Repository age: 60 days old, Sep 10, 2026. Measures age, not quality.

MODEL SIZE552B backbone · 8B active prefill / 16B active decode

LOCALRENTED GPU

Repository opened Sep 10, 2026

Text

Qwen

Qwen3.8

Explore 4 versions of Qwen3.8. Compare model sizes, packages, hardware requirements, and available setups.

4 versionsCompare sizes & formats

LOCALRENTED GPU

Compare versions →