---
title: phuongnt/VEHME
url: https://recentmodel.com/models/phuongnt/VEHME/
status: just landed · new, unvetted
published: 2026-11-02T08:24:02Z
updated: 2026-11-02T12:24:58Z
source: https://huggingface.co/phuongnt/VEHME
---

# phuongnt/VEHME

VEHME is a vision-language model for evaluating open-form handwritten mathematical solutions. Dense, 8.3B params. Context: 125K tokens (config). License: apache-2.0. Vendor-reported: "Best open-source performance: VEHME outperforms all evaluated open-source baselines across both datasets and both tasks, on Accuracy and F1."

- Vendor-reported: Best open-source performance: VEHME outperforms all evaluated open-source baselines across both datasets and both tasks, on Accuracy and F1.

- **Org:** phuongnt
- **Released:** 2026-11-02
- **Status:** just landed · new, unvetted
- **License:** apache-2.0 (permissive)
- **Parameters:** 8.3B
- **Architecture:** dense · Qwen2_5_VLForConditionalGeneration
- **Context:** 128,000 tokens
- **Task:** image-text-to-text · vision
- **Signal:** 2 HF likes · 0 downloads

## Runs on

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

- Q4 ~6.5 GB (estimated): 8GB GPU (4060 / 3070)
- Q8 ~10.3 GB (estimated): 12GB GPU (RTX 3060), 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080), 16GB GPU (7800 XT / 9070 XT), Mac 16GB, Mac 24GB
- FP16 ~18.1 GB: 24GB GPU (3090 / 4090), 32GB GPU (5090), 48GB GPU (RTX 6000 Ada / A6000), 96GB GPU (RTX Pro 6000 Blackwell), 1× DGX Spark (128GB), 2× DGX Spark (256GB), 24GB GPU (7900 XTX), Strix Halo 128GB unified (~96GB usable), Arc B60 24GB, Arc B70 32GB, Mac 36GB, Mac 48GB, Mac 64GB (M1 Max), Mac 96GB, Mac 128GB, Mac 192GB, Mac 256GB, Mac 512GB, CPU only, 32GB RAM (slow), CPU only, 64GB RAM (slow), CPU only, 128GB RAM (slow), CPU only, 256GB RAM (slow)

## Links

- [Hugging Face](https://huggingface.co/phuongnt/VEHME)