Qwen/Qwen3-VL-8B-Thinking
52 derivatives checked
- Qwen/Qwen3-VL-8B-Thinking-FP8: Quantization
- tiny-random/qwen3-vl: Different architecture
- unsloth/Qwen3-VL-8B-Thinking-GGUF: Same weights, converted (fewer layers)
- Qwen/Qwen3-VL-8B-Thinking-GGUF: Same weights, converted (fewer layers)
- unsloth/Qwen3-VL-8B-Thinking-1M-GGUF: Same weights, converted (fewer layers)
- bartowski/Qwen_Qwen3-VL-8B-Thinking-GGUF: Same weights, converted (fewer layers)
- lmstudio-community/Qwen3-VL-8B-Thinking-GGUF: Quantization (fewer layers)
- cyankiwi/Qwen3-VL-8B-Thinking-AWQ-4bit: Quantization
- Mungert/Jan-v2-VL-high-GGUF: Partial fine-tune (fewer layers)
- unsloth/Qwen3-VL-8B-Thinking-unsloth-bnb-4bit: Quantization
- mradermacher/Qwen3-VL-8B-Thinking-i1-GGUF: Quantization (fewer layers)
- mradermacher/Qwen3-VL-8B-Thinking-GGUF: Same weights, converted (fewer layers)
- nvidia/EGM-8B: Full fine-tune
- OpenWebRL/OpenWebRL-8B-SFT: Partial fine-tune
- John1604/Qwen3-VL-8B-Thinking-gguf: Quantization (fewer layers)
- redponike/Qwen3-VL-8B-Thinking-GGUF: Quantization (fewer layers)
- yujiepan/qwen3-vl-tiny-random: Different architecture
- LeadFootThrottleCock/Qwen3-VL-8B-Thinking-heretic-GGUF: Abliterated (fewer layers)
- NexaAI/Qwen3-VL-8B-Thinking-GGUF: Same weights, converted (fewer layers)
- DevQuasar/Qwen.Qwen3-VL-8B-Thinking-GGUF: Same weights, converted (fewer layers)
- Hcompany/Holo2-8B: Full fine-tune
- unsloth/Qwen3-VL-8B-Thinking: Identical copy
- unsloth/Qwen3-VL-8B-Thinking-bnb-4bit: Quantization
- nvidia/EGM-8B-SFT: Partial fine-tune
- cybermotaz/qwen3-vl-8b-thinking-nvfp4-w4a16: Quantization
- huihui-ai/Huihui-Qwen3-VL-8B-Thinking-abliterated: Abliterated
- SL-AI/GRaPE-2-Flash_GGUF: LoRA-style (fewer layers)
- spotapovadm/Qwen3-VL-8B-Thinking-GGUF: Same weights, converted (fewer layers)
- Ursulalala/HomeGuard-8B: Partial fine-tune
- coder3101/Qwen3-VL-8B-Thinking-heretic: Abliterated
4 other repos hold byte-for-byte identical weight files.