Vakamalla-Anitha/oracle19c-nl2sql-granite-4.1-3b-gguf overview
Fine Tuned Oracle 19c NL2SQL Granite 4.1 3B — GGUF A merged and quantized Q4 K M GGUF model for converting natural language requests into Oracle 19c SQL querie…
Runs locally from ~1.96 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| granite-4.1-3b-oracle19c-nl2sql-Q4_K_M.gguf | GGUF | Q4_K_M | 1.96 GB | Download |
Model Details
| Model ID | Vakamalla-Anitha/oracle19c-nl2sql-granite-4.1-3b-gguf |
|---|---|
| Author | Vakamalla-Anitha |
| Pipeline | text-generation |
| License | apache-2.0 |
| Base model | ibm-granite/granite-4.1-3b |
| Last modified | 2026-09-30T11:11:19.000Z |
Model README
---
license: apache-2.0
base_model: ibm-granite/granite-4.1-3b
pipeline_tag: text-generation
tags:
- gguf
- llama.cpp
- oracle
- oracle19c
- nl2sql
- text-to-sql
- sql-generation
- granite
- fine-tuned
---
Fine-Tuned Oracle 19c NL2SQL Granite 4.1 3B — GGUF
A merged and quantized Q4_K_M GGUF model for converting natural-language requests into Oracle 19c SQL queries.
This model was created by merging a QLoRA fine-tuned adapter with the Granite 4.1 3B base model, then converting it to GGUF format.
Download
granite-4.1-3b-oracle19c-nl2sql-Q4_K_M.gguf- Quantization: Q4_K_M
- File size: approximately 1.95 GB
Base model
Training adapter
Oracle 19c NL2SQL QLoRA Adapter
Use in LM Studio
Download the .gguf file and load it in LM Studio or another llama.cpp-compatible application.
Notes
This model is designed for Oracle 19c SQL generation. Always review generated SQL against your database schema and permissions before production use.
Run Vakamalla-Anitha/oracle19c-nl2sql-granite-4.1-3b-gguf with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models