LLM EXPLORER 57,252 MODELS INDEXED

Eagle2 9B by nvidia

By nvidia · 294 downloads
HF Repo ↗ Copy URL

Eagle2 9B is an open-source language model by nvidia. Features: 3b LLM, VRAM: 17.9GB, License: cc-by-nc-4.0.

  Arxiv:2501.14818 Base model:google/paligemma-3b... Base model:google/siglip-so400... Base model:merge:google/palige... Base model:merge:google/siglip... Base model:merge:qwen/qwen2.5-... Base model:merge:timm/convnext... Base model:qwen/qwen2.5-7b-ins... Base model:timm/convnext xxlar...   Conversational   Custom code   Eagle   Eagle chat   Feature-extraction   Image-text-to-text   Multilingual   Region:us   Safetensors   Sharded   Tensorflow   Vlm
Model Card on HF 🤗: https://huggingface.co/nvidia/Eagle2-9B 

Eagle2 9B Parameters and Internals

LLM NameEagle2 9B
Repository 🤗https://huggingface.co/nvidia/Eagle2-9B 
Base Model(s)  Paligemma 3B Mix 448   Qwen/Qwen2.5-7B-Instruct   google/siglip-so400m-patch14-384   timm/convnext_xxlarge.clip_laion2b_soup_ft_in1k   google/paligemma-3b-mix-448   Qwen/Qwen2.5-7B-Instruct   google/siglip-so400m-patch14-384   timm/convnext_xxlarge.clip_laion2b_soup_ft_in1k
Model Size3b
Required VRAM17.9 GB
Updated2026-08-10
Maintainernvidia
Model Typeeagle_chat
Model Files  4.9 GB: 1-of-4   5.0 GB: 2-of-4   5.0 GB: 3-of-4   3.0 GB: 4-of-4
Model ArchitectureEagle2ChatModel
Licensecc-by-nc-4.0
Model Max Length16384
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Torch Data Typebfloat16
Errorsreplace