Quantized Qwen 3.8 models for efficient image-text understanding (AutoRound W4A16)
Vishva R
Vishva007
AI & ML interests
Deeply interested in Generative AI, particularly Large Language Models (LLMs). Focusing on model fine-tuning, prompt engineering, and practical applications using the Hugging Face ecosystem (Transformers, Datasets).
Recent Activity
updated a model 5 days ago
Vishva007/Qwen3.5-4B-NVFP4 updated a collection 6 days ago
Qwen 3.5 updated a model 6 days ago
Vishva007/Qwen3.5-4B-W4A16-AutoRoundOrganizations
None yet
Quantized vLLM-sr's Decision 3.0 models for efficient image-text decision models (AutoRound W4A16)
-
Vishva007/d3-mini-W4A16-AutoRound
Zero-Shot Classification • 2B • Updated • 86 -
Vishva007/d3-nano-W4A16-AutoRound
Zero-Shot Classification • 1B • Updated • 35 -
Vishva007/d3-lite-W4A16-AutoRound
Zero-Shot Classification • 0.4B • Updated • 36 -
Vishva007/d3-edge-W4A16-AutoRound
Zero-Shot Classification • 0.4B • Updated • 31
Quantized Qwen 3.8 models for efficient image-text understanding (AutoRound W4A16)
Quantized vLLM-sr's Decision 3.0 models for efficient image-text decision models (AutoRound W4A16)
-
Vishva007/d3-mini-W4A16-AutoRound
Zero-Shot Classification • 2B • Updated • 86 -
Vishva007/d3-nano-W4A16-AutoRound
Zero-Shot Classification • 1B • Updated • 35 -
Vishva007/d3-lite-W4A16-AutoRound
Zero-Shot Classification • 0.4B • Updated • 36 -
Vishva007/d3-edge-W4A16-AutoRound
Zero-Shot Classification • 0.4B • Updated • 31
models 59
Vishva007/Qwen3.5-4B-NVFP4
Image-Text-to-Text • 5B • Updated • 105
Vishva007/Qwen3.5-4B-W4A16-AutoRound
2B • Updated • 97
Vishva007/Qwen3.5-4B-W4A16-AutoRound-LLM-Compressor
5B • Updated • 98
Vishva007/Qwen3.5-4B-W4A16-AutoRound-GPTQ
5B • Updated • 118
Vishva007/Qwen3.5-9B-W4A16-AutoRound-LLM-Compressor
4B • Updated • 156
Vishva007/Qwen3.5-9B-W4A16-AutoRound
2B • Updated • 193
Vishva007/Qwen3.5-9B-W4A16-AutoRound-GPTQ
2B • Updated • 410
Vishva007/Qwen3.5-9B-NVFP4
Image-Text-to-Text • 6B • Updated • 105
Vishva007/Qwen3.5-9B-W4A16-AutoRound-GPTQ-G128
5B • Updated • 38
Vishva007/Qwen3.5-0.8B-NVFP4
Image-Text-to-Text • 0.9B • Updated • 101