Tem um workflow do ComfyUI? Gere uma documentação legível direto no navegador.Torne um workflow legível.Experimentar agora ↗
This is a MXFP4MOE quantization of the model UI-Venus-1.5-30B-A3B
Fonte do modelo
Descrição da fonte
This is a MXFP4_MOE quantization of the model UI-Venus-1.5-30B-A3B
Usage Notes:
Fontes
1 fonteVerificado 10 de set.
Artefatos de modelo
4 artefatosTrechos de fonte
2 trechos--- 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
Source context: 19 downloads · 0 likes · Pipeline image-to-text · Repo noctrex/UI-Venus-1.5-30B-A3B-MXFP4_MOE-GGUF