Open Models, Ready for Production

Featured Models

All Models

37,827 results found

Model Name	Input	Output	Type
ruben3010 Qwen2-VL-7B-Instruct-AWQ-IE			Quantized	Deploy
helizac dots.ocr-4bit			Quantized	Deploy
numind NuMarkdown-8B-reasoning			Base	Deploy
JoshuaWong Nanonets-OCR-s-AWQ			Quantized	Deploy
optimum-internal-testing tiny-random-llava-next-mistral			Base	Deploy
Leeyuyu Qwen2.5-SFT2-GRPO-fundo-nothink			Base	Deploy
Hennara qwen_lora_languge_only_on_gpu			Fine-tuned	Deploy
Aravindan99 dl_650k_model_ckpt-12000			Adapter	Deploy
Anjoe AesMMIT_LLaVA_v1.5_7b_240325-hf			Base	Deploy
zhehuderek qwen2vl-7b-step50			Base	Deploy
hanchaow QTuneVL1_5-2B			Base	Deploy
Hennara qwen_lora_merged_ep_3			Fine-tuned	Deploy
hanchaow QTuneVL1_5-3B			Fine-tuned	Deploy
Leonardo6 llava-sft-freeze			Fine-tuned	Deploy
Leonardo6 llava-sft			Fine-tuned	Deploy
EZCon TLPR			Quantized	Deploy
EZCon Qwen2-VL-2B-Instruct-abliterated-4bit-mlx			Quantized	Deploy
EZCon Qwen2-VL-2B-Instruct-abliterated-8bit-mlx			Quantized	Deploy
EZCon Qwen2-VL-2B-Instruct-abliterated-mlx			Fine-tuned	Deploy
videoscore2 vs2_qwen2_5vl_sft_17k_1.5e-4_2fps_960_720_8192			Fine-tuned	Deploy
videoscore2 vs2_qwen2_5vl_sft_17k_3e-4_2fps_960_720_8192			Fine-tuned	Deploy
ncauchi1 gneral_questions_model_v8			Base	Deploy
aidan-ucc LoRA-qwen2.5VL3b-3900-720p			Fine-tuned	Deploy
aidan-ucc LoRA-qwen2.5VL3b-2600-720p			Fine-tuned	Deploy
NM-dev markdown			Base	Deploy
aidan-ucc LoRA-qwen2.5VL3b-1300-720p			Fine-tuned	Deploy
openbmb MiniCPM-V-4-int4			Base	Deploy
openbmb MiniCPM-V-4			Base	Deploy
openbmb MiniCPM-V-4-AWQ			Quantized	Deploy
natech1 boden-finetune-full			Fine-tuned	Deploy
muqtasid87 qwen2.5vl-3b-merged			Base	Deploy
natech1 boden-finetune			Fine-tuned	Deploy
ScorpieCur Qwen2.5-VL-7B-Instruct-unsloth-bnb-4bit			Quantized	Deploy
ScorpieCur Qwen2.5-VL-3B-Instruct-unsloth-bnb-4bit			Quantized	Deploy
cemoss17 vision-grpo-qwen-2.5-vl-3b			Fine-tuned	Deploy
huihui-ai Huihui-InternVL3-78B-abliterated			Fine-tuned	Deploy
tchiayan RolmOCR-bnb-4bit			Base	Deploy
cemoss17 outputs			Fine-tuned	Deploy
russellyq Qwen2.5-VL-3B-Instruct-SFT-1e			Base	Deploy
EZCon Qwen2-VL-7B-Instruct-4bit-mlx			Quantized	Deploy
EZCon Qwen2.5-VL-3B-Instruct-mlx			Fine-tuned	Deploy
videoscore2 vs2_qwen2_5vl_sft_17k_2e-4_2fps_960_720_8192_1epoch			Fine-tuned	Deploy