What are the hardware requirements for Phi2 Sqlcoder?

Phi2 Sqlcoder requires approximately 5.6 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Phi2 Sqlcoder and how large is it?

Phi2 Sqlcoder is developed by pavankumarbalijepalli, a model with 2.8b 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 Phi2 Sqlcoder?

Phi2 Sqlcoder is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Phi2 Sqlcoder by pavankumarbalijepalli — VRAM 5.6GB

Name: Phi2 Sqlcoder
Author: pavankumarbalijepalli

Phi2 Sqlcoder is an open-source language model by pavankumarbalijepalli. Features: 2.8b LLM, VRAM: 5.6GB, License: mit, Quantized, LLM Explorer Score: 0.11.

Arxiv:1910.09700 Custom code Dataset:b-mc2/sql-create-conte... Doi:10.57967/hf/1886 En Endpoints compatible Gguf Lora Nl2sql Peft Phi Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/pavankumarbalijepalli/phi2-sqlcoder

Phi2 Sqlcoder Parameters and Internals

Model Type

CASUAL_LM

Use Cases

Areas:

Generating SQL queries based on natural language questions and database schemas

Primary Use Cases:

NL2SQL automatic query generation

Limitations:

Complex logic or edge cases, Security vulnerabilities like SQL injection attacks

Considerations:

The context should be below 2048 tokens. Safety measures should be taken when using in production.

Additional Notes

The Fine-tuned Phi-2 is smaller in size, thus faster and suitable for low-powered devices.

Supported Languages

English (NLP), SQL ()

Training Details

Data Sources:

b-mc2/sql-create-context

Context Length:

2048

Input Output

Input Format:

Natural language question and relevant database schema

Accepted Modalities:

text

Output Format:

SQL query

LLM Name	Phi2 Sqlcoder
Repository 🤗	https://huggingface.co/pavankumarbalijepalli/phi2-sqlcoder
Model Size	2.8b
Required VRAM	5.6 GB
Updated	2026-07-11
Maintainer	pavankumarbalijepalli
Model Files	5.0 GB: 1-of-2 0.6 GB: 2-of-2 5.6 GB
Supported Languages	en
GGUF Quantization	Yes
Quantization Type	gguf
Model Architecture	AutoModelForCausalLM
License	mit
Model Max Length	2048
Is Biased	none
Tokenizer Class	CodeGenTokenizer
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	dense\|q_proj\|k_proj\|fc2\|fc1\|v_proj
LoRA Alpha	16
LoRA Dropout	0.05
R Param	16

Rank the Phi2 Sqlcoder 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 Phi2 Sqlcoder

Best Alternatives	Context / RAM	Downloads	Likes
Phi2 Bunny	0K / 5.6 GB	66	3
Zephyr Rag Agent Webgpt	0K / 40.1 GB	1	1
Phi 2 Electrical Engineering	0K / 5.6 GB	9	27
Phi Med V1	0K / 11.1 GB	9	1

Note: green Score (e.g. "73.2") means that the model is better than pavankumarbalijepalli/phi2-sqlcoder.