jiuhai/florence-vl-8b-sft
Updated • 1 • 21
Vision Models 12/2024 Tryout
-
-
OpenGVLab/InternVL2_5-26B-MPO
Image-Text-to-Text • 26B • Updated • 3.53k • 14 -
OpenGVLab/InternVL2_5-78B
Image-Text-to-Text • Updated • 927 • 194 -
OpenGVLab/InternVL2_5-38B
Image-Text-to-Text • 38B • Updated • 2.82k • 49 -
OpenGVLab/InternVL2_5-8B
Image-Text-to-Text • 8B • Updated • 294k • 104 -
OpenGVLab/InternVL2_5-8B-MPO
Image-Text-to-Text • 8B • Updated • 828 • 48 -
OpenGVLab/InternVL2_5-78B-MPO
Image-Text-to-Text • 78B • Updated • 30 • 54 -
Qwen/QVQ-72B-Preview
Image-Text-to-Text • 73B • Updated • 160 • 610 -
deepseek-ai/deepseek-vl2
Image-Text-to-Text • Updated • 2.19k • 381 -
deepseek-ai/deepseek-vl2-small
Image-Text-to-Text • 16B • Updated • 14.2k • 179 -
deepseek-ai/deepseek-vl2-tiny
Image-Text-to-Text • Updated • 475k • 246 -
ByteDance/Sa2VA-8B
Image-Text-to-Text • 8B • Updated • 2.73k • 65 -
ByteDance/Sa2VA-4B
Image-Text-to-Text • Updated • 1.37k • 96 -
ByteDance/Sa2VA-1B
Image-Text-to-Text • 1B • Updated • 588 • 29 -
vikhyatk/moondream2
Image-Text-to-Text • 2B • Updated • 2.46M • 1.41k -
Qwen/Qwen2-VL-7B-Instruct
Image-Text-to-Text • 8B • Updated • 1.72M • 1.27k -
Qwen/Qwen2-VL-72B-Instruct
Image-Text-to-Text • 73B • Updated • 31.1k • 309 -
Qwen/Qwen2-VL-2B-Instruct
Image-Text-to-Text • Updated • 3.44M • 498 -
meta-llama/Llama-3.2-11B-Vision-Instruct
Image-Text-to-Text • 11B • Updated • 144k • 1.59k -
microsoft/Phi-3.5-vision-instruct
Image-Text-to-Text • Updated • 1.52M • 731 -
meta-llama/Llama-3.2-90B-Vision
Image-Text-to-Text • 89B • Updated • 2.63k • 134 -
OpenGVLab/InternVL2_5-4B-MPO
Image-Text-to-Text • 4B • Updated • 22.7k • 18 -
OpenGVLab/InternVL2_5-26B
Image-Text-to-Text • 26B • Updated • 3.54k • 33 -
OpenGVLab/InternVL2_5-38B-MPO
Image-Text-to-Text • 38B • Updated • 30 • 20 -
OpenGVLab/InternVL2_5-4B
Image-Text-to-Text • 4B • Updated • 21.7k • 57 -
mistralai/Pixtral-12B-2409
Updated • 6.1k • 685 -
mistralai/Pixtral-12B-Base-2409
Updated • 10 • 108 -
mistralai/Pixtral-Large-Instruct-2411
Updated • 155 • 433 -
allenai/Molmo-7B-D-0924
Image-Text-to-Text • 8B • Updated • 20.2k • 565 -
allenai/Molmo-7B-O-0924
Image-Text-to-Text • 8B • Updated • 984 • 163 -
allenai/Molmo-72B-0924
Image-Text-to-Text • 73B • Updated • 5.29k • 298 -
allenai/MolmoE-1B-0924
Image-Text-to-Text • Updated • 5.87k • 157 -
Efficient-Large-Model/NVILA-15B
Text Generation • Updated • 91 • 25 -
microsoft/Phi-3-vision-128k-instruct
Text Generation • Updated • 115k • 971 -
zai-org/cogvlm2-llama3-chat-19B
Text Generation • 20B • Updated • 5.01k • 221 -
zai-org/cogvlm2-llama3-chat-19B-int4
Text Generation • Updated • 76 • 31 -
lmms-lab/llava-onevision-qwen2-7b-ov
Text Generation • 8B • Updated • 171k • 63 -
lmms-lab/llava-onevision-qwen2-72b-ov-chat
Image-Text-to-Text • 73B • Updated • 14 • 9 -
zai-org/glm-4v-9b
14B • Updated • 64.8k • 268 -
AIDC-AI/Ovis1.6-Gemma2-27B
Image-Text-to-Text • 29B • Updated • 27 • 62 -
AIDC-AI/Ovis1.6-Gemma2-9B
Image-Text-to-Text • Updated • 35.2k • 273 -
openbmb/MiniCPM-V-2_6
Image-Text-to-Text • 8B • Updated • 143k • 1.04k -
HuggingFaceTB/SmolVLM-Instruct
Image-Text-to-Text • 2B • Updated • 28.7k • 583 -
meta-llama/Llama-3.2-11B-Vision
Image-Text-to-Text • 11B • Updated • 13.1k • 586 -
meta-llama/Llama-3.2-90B-Vision-Instruct
Image-Text-to-Text • 89B • Updated • 12.3k • 355 -
nvidia/NVLM-D-72B
Image-Text-to-Text • Updated • 69.9k • 775 -
google/paligemma2-28b-pt-896
Image-Text-to-Text • Updated • 43 • 51 -
google/paligemma2-28b-pt-448
Image-Text-to-Text • 28B • Updated • 16 • 10 -
google/paligemma2-10b-pt-896
Image-Text-to-Text • Updated • 345 • 32 -
google/paligemma2-10b-pt-448
Image-Text-to-Text • 10B • Updated • 416 • 15 -
google/paligemma2-3b-pt-896
Image-Text-to-Text • 3B • Updated • 1k • 26 -
google/paligemma2-3b-pt-448
Image-Text-to-Text • 3B • Updated • 29.2k • 47 -
xtuner/llava-llama-3-8b-v1_1-gguf
Image-to-Text • 8B • Updated • 3.35k • 226 -
Efficient-Large-Model/NVILA-8B
Text Generation • Updated • 723 • 6 -
Efficient-Large-Model/VILA1.5-3b
Text Generation • Updated • 1.31k • 34 -
ICTNLP/llava-mini-llama-3.1-8b
Image-Text-to-Text • 9B • Updated • 290 • 58 -
openbmb/MiniCPM-o-2_6
Any-to-Any • 9B • Updated • 145k • 1.29k -
omkarthawakar/LlamaV-o1
Question Answering • 11B • Updated • 4.62k • 96 -
ByteDance/Sa2VA-26B
Image-Text-to-Text • 26B • Updated • 29 • 31 -
MiniMaxAI/MiniMax-VL-01
Image-Text-to-Text • Updated • 94.5k • 282 -
Qwen/Qwen2.5-VL-72B-Instruct
Image-Text-to-Text • 73B • Updated • 107k • • 610 -
Qwen/Qwen2.5-VL-7B-Instruct
Image-Text-to-Text • 8B • Updated • 8.87M • • 1.51k -
Qwen/Qwen2.5-VL-3B-Instruct
Image-Text-to-Text • 4B • Updated • 5.87M • 639 -
nvidia/Eagle2-9B
Image-Text-to-Text • 9B • Updated • 699 • 63 -
ibm-granite/granite-vision-3.1-2b-preview
Image-Text-to-Text • Updated • 895 • 110 -
AIDC-AI/Ovis2-34B
Image-Text-to-Text • 35B • Updated • 431 • 142 -
AIDC-AI/Ovis2-16B
Image-Text-to-Text • 16B • Updated • 160 • 98 -
AIDC-AI/Ovis2-8B
Image-Text-to-Text • 9B • Updated • 1.29k • 75 -
google/paligemma2-28b-mix-448
Image-Text-to-Text • Updated • 118 • 28 -
google/paligemma2-10b-mix-448
Image-Text-to-Text • Updated • 1.09k • 36 -
google/paligemma2-3b-mix-448
Image-Text-to-Text • Updated • 3.78k • 58 -
microsoft/Phi-4-multimodal-instruct
Automatic Speech Recognition • 6B • Updated • 348k • 1.59k -
microsoft/Magma-8B
Robotics • 9B • Updated • 1.37k • 415 -
CohereLabs/aya-vision-8b
Image-Text-to-Text • 9B • Updated • 98.1k • 320 -
CohereLabs/aya-vision-32b
Image-Text-to-Text • Updated • 52 • • 226 -
google/gemma-3-27b-it
Image-Text-to-Text • 27B • Updated • 512k • • 1.96k -
google/gemma-3-4b-it
Image-Text-to-Text • Updated • 1.98M • 1.31k -
google/gemma-3-12b-it
Image-Text-to-Text • Updated • 2.53M • • 708 -
mistralai/Mistral-Small-3.1-24B-Instruct-2503
Updated • 517k • 1.36k -
Qwen/Qwen2.5-Omni-7B
Any-to-Any • Updated • 475k • 1.89k -
meta-llama/Llama-4-Maverick-17B-128E-Instruct
Image-Text-to-Text • 402B • Updated • 30.6k • • 479 -
meta-llama/Llama-4-Scout-17B-16E-Instruct
Image-Text-to-Text • Updated • 406k • • 1.28k -
AIDC-AI/Ovis2-34B-GPTQ-Int4
Image-Text-to-Text • 35B • Updated • 174 • 8 -
Multimodal RAG with Granite Vision
🚀39RAG example using Granite [vision, embedding, instruct]
-
ibm-granite/granite-vision-3.2-2b
Image-Text-to-Text • 3B • Updated • 3.16k • 123 -
MatchAnything
🏢255Match images to find similar pictures instantly
-
Qwen/Qwen2.5-VL-32B-Instruct
Image-Text-to-Text • 33B • Updated • 79.8k • 482 -
google/siglip2-so400m-patch14-384
Zero-Shot Image Classification • Updated • 686k • 79 -
moonshotai/Kimi-VL-A3B-Thinking
Image-Text-to-Text • 16B • Updated • 106k • 447 -
moonshotai/Kimi-VL-A3B-Instruct
Image-Text-to-Text • 16B • Updated • 271k • 258 -
Junfeng5/Liquid_V1_7B
Any-to-Any • Updated • 2.96k • 94 -
facebook/Perception-LM-8B
Image-Text-to-Text • 10B • Updated • 3.59k • 67 -
Skywork/Skywork-R1V2-38B
Image-Text-to-Text • 38B • Updated • 71 • 125 -
lmms-lab/llava-onevision-qwen2-72b-si
Text Generation • 73B • Updated • 12 • 1