What are the hardware requirements for Sqlcoder 7B 2?

Sqlcoder 7B 2 requires approximately 13.5 GB of VRAM and supports a context window of 16K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Sqlcoder 7B 2 and how large is it?

Sqlcoder 7B 2 is developed by defog, a model with 7b 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 Sqlcoder 7B 2?

Sqlcoder 7B 2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Sqlcoder 7B 2 by defog — VRAM 13.5GB, 16K context

Name: Sqlcoder 7B 2
Author: defog

Sqlcoder 7B 2 is an open-source language model by defog. Features: 7b LLM, VRAM: 13.5GB, Context: 16K, License: cc-by-sa-4.0, Quantized, Instruction-Based, LLM Explorer Score: 0.17.

Deploy:azure Endpoints compatible Gguf Instruct Llama Q5 Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/defog/sqlcoder-7b-2

Sqlcoder 7B 2 Parameters and Internals

Model Type

Text to SQL

Use Cases

Primary Use Cases:

an analytics tool for non-technical users to understand data inside their SQL databases

Limitations:

not trained to reject malicious requests from users with write access, should only be used by users with read-only access

Additional Notes

This model card was automatically generated.

Release Notes

Date:

Feb 7, 2024

Notes:

The model weights were updated at 7 AM UTC, leading to a much more performant model, particularly for joins.

LLM Name	Sqlcoder 7B 2
Repository 🤗	https://huggingface.co/defog/sqlcoder-7b-2
Base Model(s)	Sqlcoder 7B 2 MLX ucalyptus/sqlcoder-7b-2-MLX
Model Size	7b
Required VRAM	13.5 GB
Updated	2026-06-09
Maintainer	defog
Model Type	llama
Instruction-Based	Yes
Model Files	4.9 GB: 1-of-3 5.0 GB: 2-of-3 3.6 GB: 3-of-3 4.8 GB 0.0 GB
GGUF Quantization	Yes
Quantization Type	q5\|gguf\|q5_k
Model Architecture	LlamaForCausalLM
License	cc-by-sa-4.0
Context Length	16384
Model Max Length	16384
Transformers Version	4.37.2
Tokenizer Class	CodeLlamaTokenizer
Vocabulary Size	32016
Torch Data Type	float16

Rank the Sqlcoder 7B 2 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

Quantized Models of the Sqlcoder 7B 2

Model	Likes	Downloads	VRAM
Sqlcoder 7B 2 GGUF	12	235	2 GB

Best Alternatives to Sqlcoder 7B 2

Best Alternatives	Context / RAM	Downloads	Likes
Lucie 7B Instruct	31K / 13.4 GB	4115	20
Lucie 7B Instruct Human Data	31K / 13.4 GB	371	7
Lucie 7B Instruct Gguf	31K / 4.1 GB	1568	4
...pseek Coder 6.7B Instruct GGUF	16K / 2.5 GB	2370	8
Sql Code Gguf	16K / 4.8 GB	25	0
... 7B Instruct Preview Reasoning	4K / 14 GB	104	3
Bailong Orpo 7B	4K / 14 GB	28	5
Latxa 7B Instruct	4K / 13.5 GB	8	0
...lumiX 32K Instruct Q4 K M GGUF	32K / 4.1 GB	89	3
...p 0.05 Max Grad1.0 Grad Accu32	32K / 14.4 GB	9	0

Note: green Score (e.g. "73.2") means that the model is better than defog/sqlcoder-7b-2.