ModelAufgelistetExtern

UI Venus 1.5 30B A3B MXFP4 MoE GGUF

This is a MXFP4MOE quantization of the model UI-Venus-1.5-30B-A3B

Quellehuggingface.co/noctrex/UI-Venus-1.5-30B-A3B-MXFP4_MOE-GGUF/tree/c35492ce2bd06059b776f841e9af3a7a5b2fd3cb

ArtOtherBasismodellinclusionAI/UI-Venus-1.5-30B-A3BVersionRevision c35492c

Modellquelle

Art: Other
Dateigröße: 1,01–15,9 GB
Basismodell: inclusionAI/UI-Venus-1.5-30B-A3B
Version: vRevision c35492c
Aktualisiert: 10. Feb. 2026
Downloads: 19
Aufgaben: Beschriftung
Quelle: Hugging Face

Quellenbeschreibung

This is a MXFP4_MOE quantization of the model UI-Venus-1.5-30B-A3B

Usage Notes:

Download the latest llama.cpp to use these quantizations.

Quellen

1 Quelle

Hugging FacePrimärVersion c35492ce2bd06059b776f841e9af3a7a5b2fd3cb

huggingface.co/noctrex/UI-Venus-1.5-30B-A3B-MXFP4_MOE-GGUF/tree/c35492ce2bd06059b776f841e9af3a7a5b2fd3cb

Verifiziert 10. Sept.

Modellartefakte

4 Artefakte

mmproj-BF16.gguf

gguf · 1,01 GB · SHA-256 c67d2c3a5284…0a41 · Hugging Face

Herunterladen

mmproj-F16.gguf

gguf · 1,01 GB · SHA-256 706549846204…7adc · Hugging Face

Herunterladen

Quellenauszüge

2 Auszüge

Readme10. Sept.huggingface.co/noctrex/UI-Venus-1.5-30B-A3B-MXFP4_MOE-GGUF

--- 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).