Qwen/Qwen3-VL-2B-Thinking
20 derivatives checked
- unsloth/Qwen3-VL-2B-Thinking-GGUF: Same weights, converted (fewer layers)
- unsloth/Qwen3-VL-2B-Thinking-1M-GGUF: Same weights, converted (fewer layers)
- furiosa-ai/Qwen3-VL-2B-Thinking: Identical copy
- Qwen/Qwen3-VL-2B-Thinking-GGUF: Same weights, converted (fewer layers)
- bartowski/Qwen_Qwen3-VL-2B-Thinking-GGUF: Same weights, converted (fewer layers)
- mradermacher/Qwen3-VL-2B-Thinking-i1-GGUF: Quantization (fewer layers)
- unsloth/Qwen3-VL-2B-Thinking-unsloth-bnb-4bit: Quantization
- mradermacher/Qwen3-VL-2B-Thinking-GGUF: Same weights, converted (fewer layers)
- lmstudio-community/Qwen3-VL-2B-Thinking-MLX-8bit: Quantization
- lmstudio-community/Qwen3-VL-2B-Thinking-GGUF: Quantization (fewer layers)
- cyankiwi/Qwen3-VL-2B-Thinking-AWQ-4bit: Quantization
- NexaAI/Qwen3-VL-2B-Thinking-GGUF: Same weights, converted (fewer layers)
- John1604/Qwen3-VL-2B-Thinking-gguf: Quantization (fewer layers)
- madrisight/MadriMed-VL-2B: Partial fine-tune
- unsloth/Qwen3-VL-2B-Thinking: Identical copy
- redponike/Qwen3-VL-2B-Thinking-GGUF: Quantization (fewer layers)
- DevQuasar/Qwen.Qwen3-VL-2B-Thinking-GGUF: Same weights, converted (fewer layers)
- madrisight/madrimed1.2-VL-2B: Partial fine-tune
- unsloth/Qwen3-VL-2B-Thinking-bnb-4bit: Quantization
- remyxai/SpaceQwen3-VL-2B-Thinking: LoRA-style
5 other repos hold byte-for-byte identical weight files.