---
title: divagr1925/QwenPU
url: https://recentmodel.com/models/divagr1925/QwenPU/
status: just landed · new, unvetted
published: 2026-10-31T09:08:19Z
updated: 2026-10-31T11:19:07Z
source: https://huggingface.co/divagr1925/QwenPU
---

# divagr1925/QwenPU

Text generation model from divagr1925 (HF pipeline tag; the card has no one-line description). Dense, 13B params. Context: 256K tokens (config). License: apache-2.0.


- **Org:** divagr1925
- **Released:** 2026-10-31
- **Status:** just landed · new, unvetted
- **License:** apache-2.0 (permissive)
- **Parameters:** 13.4B
- **Architecture:** dense · Qwen3_5ForCausalLM
- **Context:** 262,144 tokens
- **Task:** text-generation · text
- **Signal:** 3 HF likes · 0 downloads

## Runs on

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

- Q4 ~10.5 GB (estimated): 12GB GPU (RTX 3060), 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080), 16GB GPU (7800 XT / 9070 XT), Mac 16GB
- Q8 ~16.7 GB (estimated): 24GB GPU (3090 / 4090), 24GB GPU (7900 XTX), Arc B60 24GB, Mac 24GB, Mac 36GB, CPU only, 32GB RAM (slow)
- FP16 ~29.2 GB: 32GB GPU (5090), 48GB GPU (RTX 6000 Ada / A6000), 96GB GPU (RTX Pro 6000 Blackwell), 1× DGX Spark (128GB), 2× DGX Spark (256GB), Strix Halo 128GB unified (~96GB usable), Arc B70 32GB, Mac 48GB, Mac 64GB (M1 Max), Mac 96GB, Mac 128GB, Mac 192GB, Mac 256GB, Mac 512GB, CPU only, 64GB RAM (slow), CPU only, 128GB RAM (slow), CPU only, 256GB RAM (slow)

## Links

- [Hugging Face](https://huggingface.co/divagr1925/QwenPU)
- [Ollama](https://ollama.com/library/qwen)