commit a412cc5b5c0f8d4214e49b2c10ea7d538a418e25 Author: ModelHub XC Date: Sat Jun 20 04:34:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: NexaAIDev/Qwen3-VL-8B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..39484f9 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,63 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text + +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +mmproj.F16.gguf filter=lfs diff=lfs merge=lfs -text +mmproj.F32.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Instruct.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Instruct.F16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Instruct.Q5_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-8B-Instruct.Q4_K.gguf filter=lfs diff=lfs merge=lfs -text + +Qwen3VL-8B-Instruct-F16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3VL-8B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3VL-8B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +mmproj-Qwen3VL-8B-Instruct-F16.gguf filter=lfs diff=lfs merge=lfs -text +mmproj-Qwen3VL-8B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/Qwen3VL-8B-Instruct-F16.gguf b/Qwen3VL-8B-Instruct-F16.gguf new file mode 100644 index 0000000..2e9b097 --- /dev/null +++ b/Qwen3VL-8B-Instruct-F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2715c1a097f1943fb88ad59c7c0e9288a7a50c84d60cf18c6227bd9a40520972 +size 16388044896 diff --git a/Qwen3VL-8B-Instruct-Q4_K_M.gguf b/Qwen3VL-8B-Instruct-Q4_K_M.gguf new file mode 100644 index 0000000..0e94647 --- /dev/null +++ b/Qwen3VL-8B-Instruct-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67d1659bfe71b89d50b45a4ad1a9e5b997e5bb16ce5da66a6a6167abd569e9e2 +size 5027784800 diff --git a/Qwen3VL-8B-Instruct-Q8_0.gguf b/Qwen3VL-8B-Instruct-Q8_0.gguf new file mode 100644 index 0000000..f868c72 --- /dev/null +++ b/Qwen3VL-8B-Instruct-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d264b3941185d00a74f75c4245521dae088ff1efc90ab8d1754e83f5844adb0 +size 8709519456 diff --git a/README.md b/README.md new file mode 100644 index 0000000..aa19c61 --- /dev/null +++ b/README.md @@ -0,0 +1,52 @@ +--- +pipeline_tag: image-text-to-text +base_model: +- Qwen/Qwen3-VL-8B-Instruct +--- +# Qwen3-VL-8B-Instruct + +> [!NOTE] +> Note currently only [NexaSDK](https://github.com/NexaAI/nexa-sdk) supports this model's GGUF. + +Run **Qwen3-VL-8B-Instruct** optimized for CPU/GPU with [NexaSDK](https://github.com/NexaAI/nexa-sdk). + +## Quickstart + +1. **Install [NexaSDK](https://github.com/NexaAI/nexa-sdk)** +2. Run the model locally with one line of code: + + ```bash + nexa infer NexaAI/Qwen3-VL-8B-Instruct-GGUF + ``` + +## Model Description +**Qwen3-VL-8B-Instruct** is an 8-billion-parameter instruction-tuned multimodal large language model developed by the Qwen team at Alibaba Cloud. +It belongs to the **Qwen3-VL** series, designed for seamless understanding and reasoning across text, image, and video. This version combines the visual intelligence of Qwen3-VL with the instruction-following capabilities of Qwen3-LM, enabling natural, grounded conversations around complex visual content. + +Compared to the 4B variant, the **8B** model delivers stronger reasoning, richer context retention, and improved performance on visual and multilingual benchmarks while maintaining efficiency for deployment. + +## Features +- **Enhanced Visual Understanding**: Handles complex scenes, documents, and multi-image inputs. +- **Instruction-Tuned Dialogue**: Produces coherent and context-aware responses aligned with user intent. +- **Multilingual Support**: Capable of understanding and generating in multiple languages. +- **Extended Context Window**: Supports longer text and multimodal contexts for better reasoning continuity. +- **Optimized Performance**: Balances large-scale reasoning capability with deployability for high-end edge or server environments. + +## Use Cases +- Visual chatbots and multimodal assistants +- Document and chart interpretation +- Image-grounded content generation and summarization +- Video frame reasoning and analysis +- Multilingual multimodal tutoring or knowledge assistants + +## Inputs and Outputs +**Input:** +- Text, images, or combined multimodal prompts +- Optional video frames or sequential image sets + +**Output:** +- Natural-language answers, summaries, captions, or structured reasoning outputs +- Can provide visual explanations or reasoning narratives when prompted + +## License +See the [official Qwen license](https://huggingface.co/Qwen) for details on usage and redistribution. \ No newline at end of file diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..4aef15d --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "image-text-to-text", "allow_remote": true} \ No newline at end of file diff --git a/mmproj-Qwen3VL-8B-Instruct-F16.gguf b/mmproj-Qwen3VL-8B-Instruct-F16.gguf new file mode 100644 index 0000000..7ee9437 --- /dev/null +++ b/mmproj-Qwen3VL-8B-Instruct-F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca524100ebf825c9a870db1c580d03879e0da0ab2541697e2458e64891cf9d38 +size 1159029824 diff --git a/mmproj-Qwen3VL-8B-Instruct-Q8_0.gguf b/mmproj-Qwen3VL-8B-Instruct-Q8_0.gguf new file mode 100644 index 0000000..97274fd --- /dev/null +++ b/mmproj-Qwen3VL-8B-Instruct-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6ba85508d82f42590e6eb77d5340369ab6fecf107a7561d809523d8aa5f3bfd +size 752289728 diff --git a/nexa.manifest b/nexa.manifest new file mode 100644 index 0000000..c12018c --- /dev/null +++ b/nexa.manifest @@ -0,0 +1,5 @@ +{ + "ModelName":"qwen3vl", + "ModelType":"vlm", + "PluginId":"cpu_gpu" +}