Quantized Qwen 3.5 models for efficient image-text understanding (AutoRound W4A16)
-
J-Fraudster/Qwen3.5-2B-W4A16-AutoRound
Image-Text-to-Text • 1B • Updated -
J-Fraudster/Qwen3.5-2B-W4A16-AutoRound-GPTQ
Image-Text-to-Text • 2B • Updated -
J-Fraudster/Qwen3.5-2B-W4A16-AutoRound-LLM-Compressor
Image-Text-to-Text • 2B • Updated -
J-Fraudster/Qwen3.5-0.8B-W4A16-AutoRound
Image-Text-to-Text • 0.5B • Updated