# Low-resource quantization deployment

SpaceThinker-Qwen2.5VL-3B is a multimodal vision-language model focusing on spatial reasoning and visual question answering tasks.

Static quantized version of ColBERTv2.0, based on lightonai/colbertv2.0 model, offering multiple quantization options

Llama 3.2 is a multilingual large language model series developed by Meta, including 1B and 3B scale pre-trained and instruction-tuned generative models, optimized for multilingual conversation scenarios.

This is a statically quantized version based on the Llama-3.1-8B-Instuct-Uz model, supporting text generation tasks in Uzbek and English.