LLM EXPLORER 59,805 MODELS INDEXED

EGM 8B SFT by nvidia

By nvidia · 395 downloads
HF Repo ↗ Copy URL

EGM 8B SFT is an open-source language model by nvidia. Features: 8b LLM, VRAM: 17.5GB, License: apache-2.0, LLM Explorer Score: 0.25.

Base model:finetune:qwen/qwen3... Base model:qwen/qwen3-vl-8b-th...   Conversational   Deploy:azure   En   Endpoints compatible   Image-text-to-text   Multimodal   Qwen3-vl   Qwen3 vl   Region:us   Safetensors   Sharded   Supervised-fine-tuning   Tensorflow   Visual-grounding
Model Card on HF 🤗: https://huggingface.co/nvidia/EGM-8B-SFT 

EGM 8B SFT Parameters and Internals

LLM NameEGM 8B SFT
Repository 🤗https://huggingface.co/nvidia/EGM-8B-SFT 
Base Model(s)  Qwen3 VL 8B Thinking   Qwen/Qwen3-VL-8B-Thinking
Model Size8b
Required VRAM17.5 GB
Updated2026-08-10
Maintainernvidia
Model Typeqwen3_vl
Model Files  5.0 GB: 1-of-4   4.9 GB: 2-of-4   4.9 GB: 3-of-4   2.7 GB: 4-of-4   0.0 GB   0.0 GB
Supported Languagesen
Model ArchitectureQwen3VLForConditionalGeneration
Licenseapache-2.0
Model Max Length8192
Transformers Version4.57.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to EGM 8B SFT

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 VL 8B Instruct0K / 17.5 GB44943291037
Holo2 8B0K / 17.5 GB192430
Qwen3 VL 8B Instruct FP80K / 10.6 GB310860477
Qwen3vl Resume Parser0K / 17.5 GB2574553
ArmorOCR0K / 17.5 GB1959
Qwen3 VL 8B Thinking0K / 17.5 GB107015220
Qwen3 VL 8B Heretic 1.3.00K / 17.5 GB465312
Om Logistics Pod V8 8B0K / 17.5 GB1080
Om Logistics Pod V7 8B0K / 17.5 GB1250
Zhimu 1.00K / 18.6 GB1783
Note: green Score (e.g. "73.2") means that the model is better than nvidia/EGM-8B-SFT.