ST

Strands

StrandsGGUF by fabricant451Updated 2026-10-02
Download on Hugging Face
Parameters1.88B
Context4K
Layers24
Architectureqwen35
Smallest quant2.0 GB
Quick answer

Strands needs about 2.9 GB of memory at Q8_0 (a 2.0 GB file) with an 8K context window, so it fits on a 4 GB GPU.

Strands Decider v19 – a small, fast decision model for agentic AI

Strands Decider v19 is a 1.88‑billion‑parameter decision model built on Qwen3.5‑2B‑Base. It selects between options, rates items on a scale, and outputs calibrated confidence. The model is licensed under Apache‑2.0 and is available in GGUF format.

Good at

  • Decision routing in agent workflows
  • Tool selection and triage
  • Confidence‑calibrated scoring

Limits

  • No text generation, only typed decisions
  • Limited long‑document reasoning
  • Requires custom Strands‑aware llama.cpp runtime

Best for

  • Agent decision modules
  • Tool‑selection pipelines
  • Hybrid agent guardrails

Who it’s for. Developers building hybrid agents who need fast, reliable decision making. The model is ideal for systems that separate decision logic from large language generation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_02.0 GB 2.7 GB
Fits Get file →

The only available quant is Q8_0, file size 2.02 GB. It requires roughly 2.9 GB of VRAM at a 4096‑token context. With 8 GB VRAM you can run this model comfortably. No other quants are provided.

What GPU do you need for Strands?

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: the best quant that fits is Q8_0 (2.0 GB file, about 2.9 GB in use).

Which Strands quant should you choose?

Q8_0 (2.0 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters1.88B
Layers24
Trained context4,096 tokens
KV cache (fp16)48 KB per token

Source

Quantized byfabricant451
FamilyStrands
Licenseapache-2.0
Downloads (HF)849
Last updated2026-10-02

Frequently asked questions about Strands

How much VRAM does Strands need?

About 2.9 GB at Q8_0 with an 8K context window. That is the 2.0 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 Strands on an 8 GB GPU?

Yes, with Q8_0: the 2.0 GB file needs about 2.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Strands GGUF?

It depends on the quant: Q8_0 is 2.0 GB.

What context length does Strands support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.4 GB at 8K and 0.2 GB at 4K.

Where can I download Strands GGUF?

The files are on Hugging Face in the fabricant451/strands-decider-2B-hobson-v19-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 Strands 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 Strands Decider on 8 GB VRAM?

Yes. The Q8_0 quant uses about 2.9 GB of VRAM at 4096 context, leaving headroom for the runtime.

Does this model support text generation?

No. It is a typed decision model and does not generate arbitrary text.

What runtime is required?

It needs the custom Strands‑aware llama.cpp/wllama runtime; stock GGUF clients are not compatible.

Similar models

Browse all →

Other tiny models

All tiny models →