Model Intelligence Sheet
Semaj90/gemma4-legal-iq4xs-direct-gguf overview
gemma4 legal iq4xs direct GGUF Private GGUF upload for Parent Atlas offline/batch summary generation. Canonical local source path at upload time: C:\Users\jame…
Runs locally from ~4.74 GB disk (8 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 |
|---|---|---|---|---|
| gemma4-legal-iq4xs-direct.gguf | GGUF | IQ4XS | 4.74 GB | Download |
Model Details
Model README
---
license: other
library_name: llama.cpp
tags:
- gguf
- llama.cpp
- parent-atlas
- gemma4
- rotorquant
private_model: true
---
gemma4-legal-iq4xs-direct GGUF
Private GGUF upload for Parent Atlas offline/batch summary generation.
Canonical local source path at upload time:
C:\Users\james\Videos\deeds-web-app\models\gemma4-legal-iq4xs-direct.gguf
Use with llama.cpp / llama-server compatible GGUF runtimes.
Run Semaj90/gemma4-legal-iq4xs-direct-gguf with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models