Qwen/Qwen3-VL-4B-Thinking
31 derivatives checked
- Hcompany/Holo2-4B: Full fine-tune
- unsloth/Qwen3-VL-4B-Thinking-GGUF: Same weights, converted (fewer layers)
- Qwen/Qwen3-VL-4B-Thinking-GGUF: Same weights, converted (fewer layers)
- unsloth/Qwen3-VL-4B-Thinking-1M-GGUF: Same weights, converted (fewer layers)
- furiosa-ai/Qwen3-VL-4B-Thinking: Identical copy
- bartowski/Qwen_Qwen3-VL-4B-Thinking-GGUF: Same weights, converted (fewer layers)
- unsloth/Qwen3-VL-4B-Thinking-unsloth-bnb-4bit: Quantization
- Qwen/Qwen3-VL-4B-Thinking-FP8: Quantization
- ZuzeTt/Qwen3-VL-4B-Thinking-heretic-imatrix-GGUF: Abliterated (fewer layers)
- mradermacher/Qwen3-VL-4B-Thinking-GGUF: Same weights, converted (fewer layers)
- unsloth/Qwen3-VL-4B-Thinking-bnb-4bit: Quantization
- mradermacher/Qwen3-VL-4B-Thinking-i1-GGUF: Quantization (fewer layers)
- issai/Qolda-AVL-5B: Full fine-tune (fewer layers)
- lmstudio-community/Qwen3-VL-4B-Thinking-GGUF: Quantization (fewer layers)
- unsloth/Qwen3-VL-4B-Thinking: Identical copy
- TirGun/Qwen3-VL-4B-Thinking-GGUF: Quantization (fewer layers)
- nvidia/EGM-4B: Full fine-tune
- nvidia/EGM-4B-SFT: Full fine-tune
- NexaAI/Qwen3-VL-4B-Thinking-GGUF: Same weights, converted (fewer layers)
- cccccccccc418/Qwen3-VL-4B-Thinking-GGUF: Same weights, converted (fewer layers)
- DevQuasar/Qwen.Qwen3-VL-4B-Thinking-GGUF: Same weights, converted (fewer layers)
- redponike/Qwen3-VL-4B-Thinking-GGUF: Quantization (fewer layers)
- John1604/Qwen3-VL-4B-Thinking-gguf: Quantization (fewer layers)
- coder3101/Qwen3-VL-4B-Thinking-heretic: Abliterated
- prithivMLmods/Qwen3-VL-4B-Thinking-Unredacted-MAX: Abliterated
- cyankiwi/Qwen3-VL-4B-Thinking-AWQ-4bit: Quantization
- huihui-ai/Huihui-Qwen3-VL-4B-Thinking-abliterated: Abliterated
- prithivMLmods/Qwen3-VL-4B-Thinking-abliterated-v1: Abliterated
- Surpem/Supertron-VL-4B: LoRA-style
- aifeifei798/Qwen3-VL-4B-Thinking-FT-SFT: LoRA-style
7 other repos hold byte-for-byte identical weight files.