Qwen3.5-bnb-4bit - a techwithsergiu Collection

techwithsergiu 's Collections

Qwen3.5-text-gguf

Qwen3.5-text-bnb-4bit

Qwen3.5-bnb-4bit

Qwen3.5-bnb-4bit

updated Mar 6

Original f16 model → BNB 4-bit quantization for Unsloth LoRA Training

techwithsergiu/Qwen3.5-0.8B-bnb-4bit

Image-Text-to-Text • 0.9B • Updated 22 days ago • 228
techwithsergiu/Qwen3.5-2B-bnb-4bit

Image-Text-to-Text • 2B • Updated 22 days ago • 133
techwithsergiu/Qwen3.5-4B-bnb-4bit

Image-Text-to-Text • 5B • Updated 22 days ago • 276 • 1
techwithsergiu/Qwen3.5-9B-bnb-4bit

Image-Text-to-Text • 10B • Updated 22 days ago • 1.87k • 2