---
title: DavidAU/Qwen3.8-40B-Ultimate
url: https://recentmodel.com/models/DavidAU/Qwen3.8-40B-Ultimate/
status: archived · low-signal
published: 2026-10-22T00:07:26Z
updated: 2026-10-25T15:12:33Z
source: https://huggingface.co/DavidAU/Qwen3.8-40B-Ultimate
---

# DavidAU/Qwen3.8-40B-Ultimate

Image text to text model from DavidAU (HF pipeline tag; the card has no one-line description). 40B params. License: apache-2.0.


- **Org:** DavidAU
- **Released:** 2026-10-22
- **Status:** archived · low-signal
- **License:** apache-2.0 (permissive)
- **Parameters:** 40.0B
- **Task:** image-text-to-text · vision
- **Signal:** 16 HF likes · 1 downloads
- **Weights:** gated
- **Archived:** 2026-10-25 (no longer listed by the collector; stats as last seen)

## Runs on

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

- Q4 ~28.4 GB (estimated): 32GB GPU (5090), Mac 48GB
- Q8 ~46.9 GB (estimated): 48GB GPU (RTX 6000 Ada / A6000), Mac 64GB (M1 Max), Mac 96GB, CPU only, 64GB RAM (slow)
- FP16 ~84.3 GB: 96GB GPU (RTX Pro 6000 Blackwell), 1× DGX Spark (128GB), 2× DGX Spark (256GB), Strix Halo 128GB unified (~96GB usable), Mac 128GB, Mac 192GB, Mac 256GB, Mac 512GB, CPU only, 128GB RAM (slow), CPU only, 256GB RAM (slow)

## Links

- [Hugging Face](https://huggingface.co/DavidAU/Qwen3.8-40B-Ultimate)
- [Ollama](https://ollama.com/library/qwen3.8)