Model Name	Type
unsloth Qwen2.5-VL-7B-Instruct-unsloth-bnb-4bit	Quantized	Deploy
ibm-granite granite-vision-3.1-2b-preview	Fine-tuned	Deploy
bytedance-research UI-TARS-72B-DPO	Base	Deploy
HuggingFaceTB SmolVLM-500M-Instruct	Quantized	Deploy
prithivMLmods Qwen2-VL-OCR-2B-Instruct	Fine-tuned	Deploy
meta-llama Llama-3.2-11B-Vision	Base	Deploy
Qwen Qwen2.5-VL-7B-Instruct-AWQ	Quantized	Deploy
Qwen Qwen2.5-VL-72B-Instruct-AWQ	Quantized	Deploy
Qwen QVQ-72B-Preview	Fine-tuned	Deploy
MMR1 MMR1-Math-v0-7B	Fine-tuned	Deploy
homebrewltd Poseless-3B	Fine-tuned	Deploy
ds4sd SmolDocling-256M-preview	Quantized	Deploy
bytedance-research UI-TARS-7B-DPO	Base	Deploy
ibm-granite granite-vision-3.2-2b	Fine-tuned	Deploy
Qwen Qwen2.5-VL-72B-Instruct	Base	Deploy
Qwen Qwen2-VL-2B-Instruct	Fine-tuned	Deploy
Qwen Qwen2-VL-72B-Instruct	Fine-tuned	Deploy
FriendliAI pixtral-12b	Base	Deploy
google paligemma2-10b-mix-448	Base	Deploy
openbmb MiniCPM-V-2_6	Base	Deploy
facebook chameleon-7b	Base	Deploy
mistral-community pixtral-12b	Base	Deploy
llava-hf llava-1.5-7b-hf	Base	Deploy
OpenGVLab InternVL2_5-4B	Merged	Deploy
openbmb MiniCPM-Llama3-V-2_5	Base	Deploy
openbmb MiniCPM-o-2_6	Base	Deploy
microsoft Phi-3-vision-128k-instruct	Base	Deploy
allenai Molmo-7B-O-0924	Fine-tuned	Deploy
allenai Molmo-72B-0924	Fine-tuned	Deploy
allenai Molmo-7B-D-0924	Fine-tuned	Deploy
allenai olmOCR-7B-0225-preview	Fine-tuned	Deploy

Open Models, Ready for Production

Run 639,141 Open Models on the Frontier Inference Cloud.