Model Intelligence Sheet
nuofang/gemma4-e4b-mahou-nsfw-GGUF overview
Auto Quantized GGUF Model This repository contains automated GGUF quantization files for Pranavz/gemma4 e4b mahou nsfw https://huggingface.co/Pranavz/gemma4 e4…
Runs locally from ~4.2 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
7 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| gemma4-e4b-mahou-nsfw-IQ4_NL.gguf | GGUF | IQ4_NL | 4.81 GB | Download |
| gemma4-e4b-mahou-nsfw-IQ4_XS.gguf | GGUF | IQ4_XS | 4.69 GB | Download |
| gemma4-e4b-mahou-nsfw-Q4_K_M.gguf | GGUF | Q4_K_M | 4.94 GB | Download |
| gemma4-e4b-mahou-nsfw-Q4_K_S.gguf | GGUF | Q4_K_S | 4.82 GB | Download |
| gemma4-e4b-mahou-nsfw-Q5_K_M.gguf | GGUF | Q5_K_M | 5.33 GB | Download |
| gemma4-e4b-mahou-nsfw-Q5_K_S.gguf | GGUF | Q5_K_S | 5.26 GB | Download |
| imatrix.gguf | GGUF | GGUF | 4.2 MB | Download |
Model Details
Model README
---
base_model: Pranavz/gemma4-e4b-mahou-nsfw
tags:
- llama.cpp
- quantized
- imatrix
---
Auto-Quantized GGUF Model
This repository contains automated GGUF quantization files for Pranavz/gemma4-e4b-mahou-nsfw.
The calibration data for the imatrix is targeted at Chinese novels and role-playing (RP), while preserving logic and common sense.
imatrix 的校准数据以中文的小说、角色扮演为目标，同时保留逻辑和常识。
📊 Perplexity Evaluation
(Tested against the provided calibration dataset)
- Q5_K_S: PPL = 28.2787 +/- 0.30817
Run nuofang/gemma4-e4b-mahou-nsfw-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models