QW

Qwen AgentWorld 35B A3B

QwenGGUF by SC117Updated 2026-10-03
Download on Hugging Face
Parameters447M
Context256K
Layers41
Architectureqwen35moe
Smallest quant14.3 GB
Quick answer

Qwen AgentWorld 35B A3B needs about 18.5 GB of memory at its main file (a 17.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 4 quants, from 14.3 GB to 26.1 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.

Qwen AgentWorld 35B A3B – a 35B MoE world model for agentic environment simulation

Qwen AgentWorld 35B A3B is a 35B parameter language world model with 3B active per token. It supports vision and a 262,144 token context. The model is released under Apache-2.0 and is designed for agentic environment simulation.

Good at

  • Vision‑enabled world simulation
  • Long‑context reasoning up to 262,144 tokens
  • Agent‑interaction across seven domains

Limits

  • No general‑purpose daily assistant use
  • Requires large VRAM for full 35B model
  • No explicit vision model beyond basic detection

Best for

  • Simulating agent‑environment interactions
  • Testing agentic AI in controlled worlds
  • Research on multi‑domain agentic tasks

Who it’s for. Researchers and developers needing a native world model for agentic simulation. The model is not intended as a general assistant or coding tool.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—14.3 GB 15.5 GB
Too big Get file →
—17.3 GB 18.5 GB
Too big Get file →
—23.5 GB 24.7 GB
Too big Get file →
—26.1 GB 27.3 GB
Too big Get file →

For 8 GB VRAM, use the 14.27 GB file (est. 15.5 GB memory at 8k context). For 12 GB VRAM, the 17.33 GB file (18.5 GB memory) is suitable. For 16 GB VRAM, the 23.49 GB file (24.7 GB memory) or 26.13 GB file (27.3 GB memory) can be used. Estimates are approximate.

What GPU do you need for Qwen AgentWorld 35B A3B?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is the main file (14.3 GB file, about 15.5 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (17.3 GB file, about 18.5 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (26.1 GB file, about 27.3 GB in use).

Which Qwen AgentWorld 35B A3B quant should you choose?

If memory is tight, the smallest file is the first one in the table at 14.3 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35moe
Parameters447M (approximate, mixture of experts)
Active parameters3B
Layers41
Trained context262,144 tokens
KV cache (fp16)82 KB per token

Source

Quantized bySC117
FamilyQwen
Licenseapache-2.0
Downloads (HF)561
Last updated2026-10-03

Frequently asked questions about Qwen AgentWorld 35B A3B

How much VRAM does Qwen AgentWorld 35B A3B need?

About 18.5 GB at its main file with an 8K context window. That is the 17.3 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Qwen AgentWorld 35B A3B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen AgentWorld 35B A3B GGUF?

It depends on the quant: file is 14.3 GB, file is 17.3 GB, file is 23.5 GB, file is 26.1 GB.

What context length does Qwen AgentWorld 35B A3B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.8 GB at 32K.

Where can I download Qwen AgentWorld 35B A3B GGUF?

The files are on Hugging Face in the SC117/Qwen-AgentWorld-35B-A3B-MTP-APEX-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Qwen AgentWorld 35B A3B use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Qwen AgentWorld 35B A3B on 8 GB VRAM?

The 14.27 GB file requires about 15.5 GB memory at 8k context, so 8 GB VRAM is insufficient.

Does this model support vision tasks?

Yes, the model has detected vision abilities but is primarily a language world model.

What license does the model use?

The model is released under the Apache-2.0 license.

Other GGUFs of Qwen-AgentWorld-35B-A3B

Similar models

Browse all →

More from SC117

All by SC117 →

More Qwen models

All Qwen →

Other tiny models

All tiny models →