Model Intelligence Sheet
noctrex/KAT-Coder-V2.5-Dev-MXFP4_MOE-GGUF overview
This is a MXFP4 quantization with MTP of the model Kwaipilot / KAT Coder V2.5 Dev https://huggingface.co/Kwaipilot/KAT Coder V2.5 Dev Download the latest relea…
Runs locally from ~19.01 GB disk (24 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
1 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| KAT-Coder-V2.5-Dev-MTP-MXFP4_MOE.gguf | GGUF | GGUF | 19.01 GB | Download |
Model Details
| Model ID | noctrex/KAT-Coder-V2.5-Dev-MXFP4_MOE-GGUF |
|---|---|
| Author | noctrex |
| Pipeline | text-generation |
| License | — |
| Base model | Kwaipilot/KAT-Coder-V2.5-Dev |
| Last modified | 2026-07-27T21:40:22.000Z |
Model README
---
pipeline_tag: text-generation
base_model:
- Kwaipilot/KAT-Coder-V2.5-Dev
---
This is a MXFP4 quantization with MTP of the model Kwaipilot / KAT-Coder-V2.5-Dev
Download the latest release of llama.cpp in order to use the model.
Run noctrex/KAT-Coder-V2.5-Dev-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