Model Intelligence Sheet
build-small-hackathon/lfed-qwen2.5-coder-14b-sql-gguf overview
LFED v2 — Qwen2.5 Coder 14B Text to SQL GGUF Fine tuned QLoRA r=32 on 27,859 NL→SQL pairs for DuckDB SQL generation from natural language questions about schoo…
Runs locally from ~8.37 GB disk (12 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 |
|---|---|---|---|---|
| lfed-qwen2.5-coder-14b-sql-Q4_K_M.gguf | GGUF | Q4_K_M | 8.37 GB | Download |
Model Details
| Model ID | build-small-hackathon/lfed-qwen2.5-coder-14b-sql-gguf |
|---|---|
| Author | build-small-hackathon |
| Pipeline | text-generation |
| License | apache-2.0 |
| Base model | — |
| Last modified | 2026-06-11T03:33:09.000Z |
Model README
---
tags:
- text-to-sql
- education
- local-first
- llama-cpp
- duckdb
- gguf
- qwen
- qlora
language: en
license: apache-2.0
pipeline_tag: text-generation
---
LFED v2 — Qwen2.5-Coder-14B Text-to-SQL (GGUF)
Fine-tuned QLoRA (r=32) on 27,859 NL→SQL pairs for DuckDB SQL generation
from natural-language questions about school district data.
Base model: Qwen2.5-Coder-14B-Instruct
Format: GGUF Q4_K_M
Use with: llama.cpp, Ollama, LM Studio
Run build-small-hackathon/lfed-qwen2.5-coder-14b-sql-gguf with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models