What are the hardware requirements for Sqlcoder2 GPTQ?

Sqlcoder2 GPTQ requires approximately 9.2 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Sqlcoder2 GPTQ and how large is it?

Sqlcoder2 GPTQ is developed by TheBloke, a model with 15.8b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Sqlcoder2 GPTQ?

Sqlcoder2 GPTQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Sqlcoder2 GPTQ by TheBloke — VRAM 9.2GB

Name: Sqlcoder2 GPTQ
Author: TheBloke

Sqlcoder2 GPTQ is an open-source language model by TheBloke. Features: 15.8b LLM, VRAM: 9.2GB, License: other, Quantized, Code Generating, LLM Explorer Score: 0.09.

4-bit Base model:defog/sqlcoder2 Base model:quantized:defog/sql... Code Codegen En Gpt bigcode Gptq Quantized Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/TheBloke/sqlcoder2-GPTQ

Sqlcoder2 GPTQ Parameters and Internals

Model Type

text-generation, natural language to SQL conversion

Use Cases

Areas:

Research, Commercial applications

Primary Use Cases:

Natural language to SQL generation tasks

Limitations:

Requires tuning on specific schemas for optimal performance.

Additional Notes

Fine-tuning on a given schema enhances performance.

Supported Languages

en (Primary language for model tasks)

Training Details

Data Sources:

20,000 human-curated questions based on 10 different schemas

Methodology:

Fine-tuned on a base StarCoder model

Hardware Used:

Tested on an A100 40GB GPU with bfloat16 weights

Input Output

Input Format:

Formatted prompt with task and database schema.

Accepted Modalities:

text

Output Format:

SQL query

Performance Tips:

Using specific schema tuning enhances model performance.

LLM Name	Sqlcoder2 GPTQ
Repository 🤗	https://huggingface.co/TheBloke/sqlcoder2-GPTQ
Model Name	Sqlcoder2
Model Creator	Defog.ai
Base Model(s)	Sqlcoder2 defog/sqlcoder2
Model Size	15.8b
Required VRAM	9.2 GB
Updated	2026-05-29
Maintainer	TheBloke
Model Type	gpt_bigcode
Model Files	9.2 GB
Supported Languages	en
GPTQ Quantization	Yes
Quantization Type	gptq
Generates Code	Yes
Model Architecture	GPTBigCodeForCausalLM
License	other
Transformers Version	4.34.0
Tokenizer Class	GPT2Tokenizer
Vocabulary Size	49152
Torch Data Type	float16
Activation Function	gelu

Rank the Sqlcoder2 GPTQ capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Sqlcoder2 GPTQ

Best Alternatives	Context / RAM	Downloads	Likes
Sqlcoder GPTQ	0K / 9.2 GB	11	9
Octocoder GPTQ	0K / 9.2 GB	6	8
Redmond Hermes Coder GPTQ	0K / 9.2 GB	51	10
Starchat Beta GPTQ	0K / 8.9 GB	57	27
Starcoderplus GPTQ	0K / 8.9 GB	52	25
Starcoder GPTQ	0K / 8.9 GB	67	13