GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
nvidia
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
nvidia
Model Tree
Qwen/Qwen3-VL-4B-Thinking
Input Modalities
Output Modalities
Supported Functionality
EGM-Qwen3-VL-4B-SFT is the supervised fine-tuning (SFT) checkpoint from the first stage of the EGM (Efficient Visual Grounding Language Models) training pipeline. It is built on top of Qwen3-VL-4B-Thinking.
This is an intermediate checkpoint intended for further reinforcement learning training. For the final model with best performance, see nvidia/EGM-4B.
In the SFT stage, a proprietary VLM generates detailed chain-of-thought reasoning steps for visual grounding training data. The base Qwen3-VL-4B-Thinking model is then fine-tuned on this reasoning-augmented data to learn structured visual grounding with explicit reasoning.
This SFT checkpoint serves as the initialization for the subsequent RL stage (GRPO), which yields the final EGM-4B model.
bash
pip install -U huggingface_hubhuggingface-cli download nvidia/EGM-4B-SFT --local-dir ./models/EGM-4B-SFT
Then follow the installation and RL training instructions in the EGM repository.
| Component | Details |
|---|---|
| Architecture | Qwen3VLForConditionalGeneration |
| Precision | bfloat16 |
| Text Hidden Size | 2560 |
| Text Layers | 36 |
| Attention Heads | 32 (8 KV heads) |
| Text Intermediate Size | 9728 |
| Vision Hidden Size | 1024 |
| Vision Layers | 24 |
| Patch Size | 16 x 16 |
| Model | Description |
|---|---|
| nvidia/EGM-4B | Final RL-trained model (best performance) |
| nvidia/EGM-8B-SFT | SFT checkpoint for the 8B variant |
| nvidia/EGM-8B | Final RL-trained 8B model |
bibtex
@article{zhan2026EGM,author = {Zhan, Guanqi and Li, Changye and Liu, Zhijian and Lu, Yao and Wu, Yi and Han, Song and Zhu, Ligeng},title = {EGM: Efficient Visual Grounding Language Models},booktitle = {arXiv},year = {2026}}
This repository benefits from Qwen3-VL, InternVL, verl and verl-internvl.
| Max Position Embeddings | 262,144 |
| Vocabulary Size | 151,936 |