31 Downloads Updated 3 days ago
ollama pull RizwanMalik/qwen3-vl-embedding-2b:q4_0-q8_0
Name
4 models
qwen3-vl-embedding-2b:q4_0-q8_0
1.5GB · 256K context window · Text, Image · 3 days ago
qwen3-vl-embedding-2b:q4_k_m-q8_0
1.5GB · 256K context window · Text, Image · 3 days ago
qwen3-vl-embedding-2b:q5_k_m-q8_0
1.7GB · 256K context window · Text, Image · 3 days ago
qwen3-vl-embedding-2b:q8_0-q8_0
2.3GB · 256K context window · Text, Image · 3 days ago
qwen embedding
This wont run in ollama , cause ollama has not support for multimodal embedding, it will crash, download the model form the huggingface and use llama.cpp to inference it
Rizwan313/Qwen3-VL-Embedding-2B-GGUF. –> hugging face