---
title: masterset-ai/PhysicalEye-Decide-35B
url: https://recentmodel.com/models/masterset-ai/PhysicalEye-Decide-35B/
status: archived · low-signal
published: 2026-10-10T03:22:49Z
updated: 2026-10-24T11:24:09Z
source: https://huggingface.co/masterset-ai/PhysicalEye-Decide-35B
---

# masterset-ai/PhysicalEye-Decide-35B

PhysicalEye-Decide-35B is a decision engine for images. Mixture-of-experts, 35B total, 3B active (256 experts, 8 per token). Context: 256K tokens (config). License: apache-2.0.


- **Org:** masterset-ai
- **Released:** 2026-10-10
- **Status:** archived · low-signal
- **License:** apache-2.0 (permissive)
- **Parameters:** 34.6B total, 3.0B active
- **Architecture:** MoE · 256 experts, 8/token · Qwen3_5MoeModel
- **Context:** 262,144 tokens
- **Task:** image-text-to-text · vision
- **Signal:** 2 HF likes · 98 downloads
- **Archived:** 2026-10-24 (low-signal: aged out below threshold; stats as last seen)

## Runs on

estimate from params; sizing calculation, not tested.

- Q4 ~22.5 GB (estimated): 24GB GPU (3090 / 4090), 32GB GPU (5090), 24GB GPU (7900 XTX), Mac 36GB, Mac 48GB, CPU only, 32GB RAM (slow)
- Q8 ~38.5 GB (estimated): 48GB GPU (RTX 6000 Ada / A6000), Mac 64GB (M1 Max), CPU only, 64GB RAM (slow)
- FP16 ~70.9 GB (estimated): 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/masterset-ai/PhysicalEye-Decide-35B)