What are the hardware requirements for Nsql 6B?

Nsql 6B requires approximately 28.4 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Nsql 6B and how large is it?

Nsql 6B is developed by NumbersStation, a model with 6b 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 Nsql 6B?

Nsql 6B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Nsql 6B by NumbersStation — VRAM 28.4GB

Name: Nsql 6B
Author: NumbersStation

Nsql 6B is an open-source language model by NumbersStation. Features: 6b LLM, VRAM: 28.4GB, License: bsd-3-clause, Code Generating, LLM Explorer Score: 0.08.

Codegen Endpoints compatible Pytorch Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/NumbersStation/nsql-6B

Nsql 6B Parameters and Internals

Model Type

autoregressive, text-to-SQL generation

Use Cases

Areas:

SQL generation tasks

Applications:

Database querying, Natural language to SQL conversion

Primary Use Cases:

Text-to-SQL generation, Database query formation

Considerations:

The model should be used with the defined prompt format for optimal results.

Additional Notes

Model is fine-tuned for SQL generation with predefined prompt format and designed to output SELECT queries.

Training Details

Data Sources:

The Stack, 20 public sources for text-to-SQL pairs

Data Volume:

1M training samples from The Stack

Methodology:

Cross-entropy loss for SQL generation tasks

Hardware Used:

80GB A100s

Model Architecture:

Autoregressive model

LLM Name	Nsql 6B
Repository 🤗	https://huggingface.co/NumbersStation/nsql-6B
Model Size	6b
Required VRAM	28.4 GB
Updated	2026-07-30
Maintainer	NumbersStation
Model Type	codegen
Model Files	10.0 GB: 1-of-3 10.0 GB: 2-of-3 8.4 GB: 3-of-3 10.0 GB: 1-of-3 10.0 GB: 2-of-3 8.4 GB: 3-of-3
Generates Code	Yes
Model Architecture	CodeGenForCausalLM
License	bsd-3-clause
Model Max Length	2048
Transformers Version	4.28.1
Tokenizer Class	GPT2Tokenizer
Vocabulary Size	51200
Torch Data Type	float32
Activation Function	gelu_new

Rank the Nsql 6B 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 Nsql 6B

Best Alternatives	Context / RAM	Downloads	Likes
...egen 6B Nl Lora Adapter Merged	0K / 14.3 GB	3	1
...en 6B Mono Lora Adapter Merged	0K / 14.3 GB	5	0
Codegen 6B Multi	0K / 14.3 GB	951	20
Diff Codegen 6B V2	0K / 14.3 GB	22	40
...en 6B Mono Instruct Py Revised	0K / 28.4 GB	5	2
...n 6B Mono Instruct Py Critique	0K / 28.4 GB	4	2
...gen 6B Nl Instruct Py Critique	0K / 28.4 GB	6	1
Codegen 6B Nl	0K / 14.3 GB	146	4
CodeGen RE	0K / 28.8 GB	5	2
Fine Tuned Codegen 6B Verilog	0K / 28.4 GB	14	2