---
title: perplexity-ai/pplx-decider-v1.3
url: https://recentmodel.com/models/perplexity-ai/pplx-decider-v1.3/
status: just landed
published: 2026-11-09T08:38:41Z
updated: 2026-11-13T00:29:33Z
source: https://huggingface.co/perplexity-ai/pplx-decider-v1.3
---

# perplexity-ai/pplx-decider-v1.3

pplx-decider-v1.3 is the next version of pplx-decider-v1.2, a multimodal classification model on Qwen3.8-27B. Dense, 26B params. Context: 256K tokens (config). License: apache-2.0.


- **Org:** perplexity-ai
- **Released:** 2026-11-09
- **Status:** just landed
- **License:** apache-2.0 (permissive)
- **Parameters:** 26.1B
- **Architecture:** dense · Qwen3_5Model
- **Context:** 262,144 tokens (config.json)
- **Task:** text-classification · text
- **Signal:** 34 HF likes · 477 downloads

## Runs on

mixed: real files + estimate; sizing calculation, not tested.

- Q4 ~18.8 GB (estimated): 24GB GPU (3090 / 4090), 24GB GPU (7900 XTX), Mac 36GB, CPU only, 32GB RAM (slow)
- Q8 ~30.8 GB (estimated): 32GB GPU (5090), 48GB GPU (RTX 6000 Ada / A6000), Arc B70 32GB, Mac 48GB, Mac 64GB (M1 Max), CPU only, 64GB RAM (slow)
- FP16 ~57.2 GB: 96GB GPU (RTX Pro 6000 Blackwell), 1× DGX Spark (128GB), 2× DGX Spark (256GB), Strix Halo 128GB unified (~96GB usable), Mac 96GB, Mac 128GB, Mac 192GB, Mac 256GB, Mac 512GB, CPU only, 128GB RAM (slow), CPU only, 256GB RAM (slow)

## Links

- [Hugging Face](https://huggingface.co/perplexity-ai/pplx-decider-v1.3)
- [Ollama](https://ollama.com/library/pplx-decider)