Qwen/Qwen3-VL-2B-Instruct
103 derivatives checked
- Qwen/Qwen3-VL-Embedding-2B: LoRA-style
- typhoon-ai/typhoon-ocr1.5-2b: Full fine-tune
- Qwen/Qwen3-VL-Reranker-2B: LoRA-style
- cyankiwi/Qwen3-VL-2B-Instruct-AWQ-4bit: Quantization
- unsloth/Qwen3-VL-2B-Instruct-GGUF: Same weights, converted (fewer layers)
- bartowski/Qwen_Qwen3-VL-2B-Instruct-GGUF: Same weights, converted (fewer layers)
- unsloth/Qwen3-VL-2B-Instruct-unsloth-bnb-4bit: Quantization
- mobilint/Qwen3-VL-2B-Instruct: Full fine-tune (fewer layers)
- ggml-org/Qwen3-VL-2B-Instruct-GGUF: Quantization (fewer layers)
- Qwen/Qwen3-VL-2B-Instruct-FP8: Quantization
- unsloth/Qwen3-VL-2B-Instruct: Identical copy
- phxember/Uni-MuMER-Qwen3-VL-2B: Full fine-tune
- FireRedTeam/FireRed-OCR: Partial fine-tune
- unsloth/Qwen3-VL-2B-Instruct-1M-GGUF: Same weights, converted (fewer layers)
- furiosa-ai/Qwen3-VL-2B-Instruct: Identical copy
- lmstudio-community/Qwen3-VL-2B-Instruct-GGUF: Quantization (fewer layers)
- geolazagr/greko: Full fine-tune (fewer layers)
- unsloth/Qwen3-VL-2B-Instruct-bnb-4bit: Quantization
- ADSKAILab/Zero-To-CAD-Qwen3-VL-2B: Full fine-tune
- rokotmidi/rokot-omr-2b: Full fine-tune
- saidutta69/Qwen3-VL-2B-Instruct-heretic: Abliterated
- mlx-community/Qwen3-VL-Embedding-2B-8bit: Quantization
- mradermacher/Qwen3-VL-2B-Instruct-i1-GGUF: Quantization (fewer layers)
- huihui-ai/Huihui-Qwen3-VL-2B-Instruct-abliterated: Abliterated
- taobao-mnn/Qwen3-VL-2B-Instruct-Eagle3: Different architecture
- lmstudio-community/Qwen3-VL-2B-Instruct-MLX-8bit: Quantization
- lmstudio-community/Qwen3-VL-2B-Instruct-MLX-bf16: Same weights, repacked
- Arm/qwen3-vl-2b-instruct-q4-k-m-ggml-llama-cpp-vivo-x300: Quantization (fewer layers)
- MCG-NJU/TimeLens2-2B: Partial fine-tune
- mohajesmaeili/Qwen3-VL-2B-Persian-Arabic-Ocr-v1.0: LoRA-style
22 other repos hold byte-for-byte identical weight files.