---
title: endless-frontier/Fx-Phys
url: https://recentmodel.com/models/endless-frontier/Fx-Phys/
status: just landed · new, unvetted
published: 2026-10-24T08:28:31Z
updated: 2026-10-24T11:24:09Z
source: https://huggingface.co/endless-frontier/Fx-Phys
---

# endless-frontier/Fx-Phys

Fx-Phys is a 35B-class multimodal language model for research-level physics reasoning. Mixture-of-experts, 36B total, 3B active (256 experts, 8 per token). Context: 256K tokens (config). License: apache-2.0. Vendor-reported: "It also surpasses DeepSeek-V4-Pro-Preview on all six benchmarks in this comparison."

- Vendor-reported: It also surpasses DeepSeek-V4-Pro-Preview on all six benchmarks in this comparison.

- **Org:** endless-frontier
- **Released:** 2026-10-24
- **Status:** just landed · new, unvetted
- **License:** apache-2.0 (permissive)
- **Parameters:** 36.0B total, 3.0B active
- **Architecture:** MoE · 256 experts, 8/token · Qwen3_5MoeForConditionalGeneration
- **Context:** 262,144 tokens
- **Task:** image-text-to-text · vision
- **Signal:** 2 HF likes · 26 downloads

## Runs on

real quant files; sizing calculation, not tested.

- Q4 ~23.4 GB: 32GB GPU (5090), Mac 36GB, Mac 48GB, CPU only, 32GB RAM (slow)
- Q8 ~40.1 GB: 48GB GPU (RTX 6000 Ada / A6000), Mac 64GB (M1 Max), Mac 96GB, CPU only, 64GB RAM (slow)
- FP16 ~73.6 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/endless-frontier/Fx-Phys)