Qwen/Qwen2.5-VL-7B-Instruct
333 derivatives checked
- Qwen/Qwen2.5-VL-7B-Instruct-AWQ: Quantization
- nvidia/Qwen2.5-VL-7B-Instruct-NVFP4: Quantization
- huihui-ai/Qwen2.5-VL-7B-Instruct-abliterated: Abliterated
- unsloth/Qwen2.5-VL-7B-Instruct-GGUF: Same weights, converted (fewer layers)
- numind/NuMarkdown-8B-Thinking: Full fine-tune
- allenai/olmOCR-2-7B-1025-FP8: Quantization
- allenai/olmOCR-2-7B-1025: Full fine-tune
- lmstudio-community/Qwen2.5-VL-7B-Instruct-GGUF: Quantization (fewer layers)
- ggml-org/Qwen2.5-VL-7B-Instruct-GGUF: Same weights, converted (fewer layers)
- RedHatAI/Qwen2.5-VL-7B-Instruct-FP8-Dynamic: Quantization
- mradermacher/Qwen2.5-VL-7B-Instruct-GGUF: Same weights, converted (fewer layers)
- nvidia/Cosmos-Reason1-7B: Full fine-tune
- mlx-community/Qwen2.5-VL-7B-Instruct-4bit: Quantization
- RedHatAI/Qwen2.5-VL-7B-Instruct-quantized.w8a8: Quantization
- bartowski/Qwen_Qwen2.5-VL-7B-Instruct-GGUF: Same weights, converted (fewer layers)
- allenai/olmOCR-7B-0825-FP8: Quantization
- unsloth/Qwen2.5-VL-7B-Instruct-unsloth-bnb-4bit: Quantization
- xlangai/OpenCUA-7B: Full fine-tune
- unsloth/Qwen2.5-VL-7B-Instruct: Same weights, repacked
- unsloth/Qwen2.5-VL-7B-Instruct-bnb-4bit: Quantization
- NOVAglow646/Monet-7B: Full fine-tune
- Kwai-Keye/Thyme-RL: Full fine-tune
- Word2Li/Electricity-Meter-OCR-7B: Partial fine-tune
- typhoon-ai/typhoon-ocr-7b: Full fine-tune
- TIGER-Lab/VideoScore2: Full fine-tune
- IDEA-Research/Rex-Thinker-GRPO-7B: Partial fine-tune
- TianheWu/VisualQuality-R1-7B: Partial fine-tune
- hfl/Qwen2.5-VL-7B-Instruct-GPTQ-Int4: Quantization
- reducto/RolmOCR: Full fine-tune
- mlx-community/Qwen2.5-VL-7B-Instruct-8bit: Quantization
28 other repos hold byte-for-byte identical weight files.