WO

Woof Selector 4B

WoofGGUF by ConwayResearchUpdated 2026-10-06
Download on Hugging Face
Parameters4.21B
Context256K
Layers32
Architectureqwen35
Smallest quant2.7 GB
Quick answer

Woof Selector 4B needs about 4.3 GB of memory at its main file (a 2.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Woof Selector 4B 4-bit v2.1 – a compact browser‑use model

Woof Selector 4B is a 4.21B parameter model built on Qwen3.5-4B. It is trained for 4‑bit deployment and focuses on selecting the next browser action. The model has 262144 trained context tokens and is licensed under apache‑2.0.

Good at

  • Browser task selection
  • Reasoning
  • Tool usage

Limits

  • No vision support
  • Limited context to 262144 tokens
  • Single‑step validation only

Best for

  • Automating web browsing
  • Choosing next browser action
  • Local browser assistants

Who it’s for. Developers building local browser assistants who need a lightweight, 4‑bit model for action selection. The model is suitable for Apple Silicon and other local deployments.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—2.7 GB 4.3 GB
Fits Get file →

The only available GGUF file is 2.71 GB with an estimated 4.3 GB VRAM requirement at 8 k context. This is suitable for systems with at least 8 GB VRAM. No other quantizations are provided.

What GPU do you need for Woof Selector 4B?

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: the best quant that fits is the main file (2.7 GB file, about 4.3 GB in use).

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters4.21B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized byConwayResearch
FamilyWoof
Licenseapache-2.0
Downloads (HF)453
Last updated2026-10-06

Frequently asked questions about Woof Selector 4B

How much VRAM does Woof Selector 4B need?

About 4.3 GB at its main file with an 8K context window. That is the 2.7 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 Woof Selector 4B on an 8 GB GPU?

Yes, with the smaller files: the 2.7 GB file needs about 4.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Woof Selector 4B GGUF?

It depends on the quant: file is 2.7 GB.

What context length does Woof Selector 4B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Woof Selector 4B GGUF?

The files are on Hugging Face in the ConwayResearch/woof-selector-4B-4bit-v2.1 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Woof Selector 4B 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 Woof Selector 4B on 8 GB VRAM?

Yes, the model requires an estimated 4.3 GB VRAM at 8 k context, so 8 GB VRAM is sufficient.

Does the model support vision tasks?

No, Woof Selector 4B does not support vision.

What license does the model use?

The model is released under the apache‑2.0 license.

Similar models

Browse all →

More from ConwayResearch

All by ConwayResearch →

More Woof models

All Woof →

Other small models

All small models →