Koshkasa/Vortex5_G4-Dark-Soul-26B-A4B-MXFP4_MoE-GGUF overview
What's that? MXFP4 MOE quantization of the emerging roleplay workhorse Vortex5/G4 Dark Soul 26B A4B https://huggingface.co/Vortex5/G4 Dark Soul 26B A4B Use cas…
Runs locally from ~13.72 GB disk (16 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| G4-Dark-Soul-26B-A4B-mxfp4_moe.gguf | GGUF | GGUF | 13.72 GB | Download |
Model Details
| Model ID | Koshkasa/Vortex5_G4-Dark-Soul-26B-A4B-MXFP4_MoE-GGUF |
|---|---|
| Author | Koshkasa |
| Pipeline | text-generation |
| License | apache-2.0 |
| Base model | Vortex5/G4-Dark-Soul-26B-A4B |
| Last modified | 2026-07-31T06:45:26.000Z |
Model README
---
license: apache-2.0
base_model:
- Vortex5/G4-Dark-Soul-26B-A4B
library_name: ik_llama.cpp
pipeline_tag: text-generation
tags:
- gguf
- quantized
- llama.cpp
- roleplay
- mxfp4
quantized_by: Koshkasa
base_model_relation: quantized
---
What's that?
MXFP4_MOE quantization of the emerging roleplay workhorse Vortex5/G4-Dark-Soul-26B-A4B
Use case
Running the model on consumer-grade Blackwell GPUs with 16gb+ of VRAM.
Disclosure
My only contribution is compute. This is not my merge. Have fun.
Cheers
Google - the base model.
Vortex5 - for the merge effort.
Everyone whose finetunes were included in the merge!
Run Koshkasa/Vortex5_G4-Dark-Soul-26B-A4B-MXFP4_MoE-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models