README.md

metadata

title: GRACE-VLM
emoji: 🦢
colorFrom: blue
colorTo: purple
sdk: static
app_file: index.html
pinned: true
short_description: Deployable INT4 Qwen3-VL through GRACE distillation.
models:
  - ForeverBlue/Qwen3-VL-2B-GRACE-W4G128-AWQ
  - ForeverBlue/Qwen3-VL-2B-GRACE-BF16
tags:
  - vision-language-model
  - multimodal
  - int4
  - awq
  - knowledge-distillation
  - arxiv:2601.22709

GRACE-VLM

Project showcase for GRACE-VLM: INT4 Quantization-Aware Distillation for Vision-Language Models, accepted at ICML 2026. Read the paper at arXiv:2601.22709.

This free static Space presents the benchmark results, a model output, and the copy-ready real INT4 deployment command. Interactive inference requires hosted GPU hardware; the model and loader remain fully available for local deployment.