This is a MXFP4MOE quantization of the model UI-Venus-1.5-30B-A3B
Model source
Source description
This is a MXFP4_MOE quantization of the model UI-Venus-1.5-30B-A3B
Usage Notes:
Sources
1 sourceVerified Sep 10
Model artifacts
4 artifactsSource excerpts
2 excerpts--- pipeline_tag: image-to-text base_model: - inclusionAI/UI-Venus-1.5-30B-A3B --- This is a MXFP4_MOE quantization of the model [UI-Venus-1.5-30B-A3B](https://huggingface.co/inclusionAI/UI-Venus-1.5-30B-A3B) **Usage Notes:** - Download the latest [llama.cpp](https://github.com/ggml-org/llama.cpp) to use these quantizations. - Try to use the best quality you can run. - For the `mmproj` file, the F32 version is recommended for best results (F32 > BF16 > F16).
mmproj file, the F32 version is recommended for best results (F32 > BF16 > F16).mmproj-F32.gguf
gguf · 2.01 GB · SHA-256 00584ee78709…9795 · Hugging Face
UI-Venus-1.5-30B-A3B-MXFP4_MOE.gguf
gguf · 15.9 GB · SHA-256 f55a7b11b0ec…bca7 · Hugging Face
DownloadSource context: 19 downloads · 0 likes · Pipeline image-to-text · Repo noctrex/UI-Venus-1.5-30B-A3B-MXFP4_MOE-GGUF