What are the hardware requirements for Spider Natsql Wizard Coder Merged?

Spider Natsql Wizard Coder Merged requires approximately 32.7 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Spider Natsql Wizard Coder Merged and how large is it?

Spider Natsql Wizard Coder Merged is developed by richardr1126, a model with 15b 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 Spider Natsql Wizard Coder Merged?

Spider Natsql Wizard Coder Merged is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Spider Natsql Wizard Coder Merged by richardr1126 — VRAM 32.7GB

Name: Spider Natsql Wizard Coder Merged
Author: richardr1126

Spider Natsql Wizard Coder Merged is an open-source language model by richardr1126. Features: 15b LLM, VRAM: 32.7GB, License: bigcode-openrail-m, Instruction-Based, Code Generating, LLM Explorer Score: 0.07.

Arxiv:1809.08887 Arxiv:2109.05153 Arxiv:2305.14314 Codegen Codegen Dataset:richardr1126/spider-na... Dataset:spider Endpoints compatible Gpt bigcode Instruct Pytorch Region:us Sharded Spider Sql Sql Sql finetune

Model Card on HF 🤗: https://huggingface.co/richardr1126/spider-natsql-wizard-coder-merged

Spider Natsql Wizard Coder Merged Parameters and Internals

Use Cases

Areas:

text-to-SQL

Additional Notes

This model was finetuned on a NatSQL enhanced Spider context training dataset.

Training Details

Data Sources:

richardr1126/spider-natsql-context-instruct

Methodology:

Finetuning was performed using QLoRa on a single RTX6000 48GB

Hardware Used:

RTX6000 48GB

LLM Name	Spider Natsql Wizard Coder Merged
Repository 🤗	https://huggingface.co/richardr1126/spider-natsql-wizard-coder-merged
Model Size	15b
Required VRAM	32.7 GB
Updated	2026-07-14
Maintainer	richardr1126
Model Type	gpt_bigcode
Instruction-Based	Yes
Model Files	0.9 GB: 1-of-41 0.8 GB: 2-of-41 0.8 GB: 3-of-41 0.8 GB: 4-of-41 0.8 GB: 5-of-41 0.8 GB: 6-of-41 0.8 GB: 7-of-41 0.8 GB: 8-of-41 0.8 GB: 9-of-41 0.8 GB: 10-of-41 0.8 GB: 11-of-41 0.8 GB: 12-of-41 0.8 GB: 13-of-41 0.8 GB: 14-of-41 0.8 GB: 15-of-41 0.8 GB: 16-of-41 0.8 GB: 17-of-41 0.8 GB: 18-of-41 0.8 GB: 19-of-41 0.8 GB: 20-of-41 0.8 GB: 21-of-41 0.8 GB: 22-of-41 0.8 GB: 23-of-41 0.8 GB: 24-of-41 0.8 GB: 25-of-41 0.8 GB: 26-of-41 0.8 GB: 27-of-41 0.8 GB: 28-of-41 0.8 GB: 29-of-41 0.8 GB: 30-of-41 0.8 GB: 31-of-41 0.8 GB: 32-of-41 0.8 GB: 33-of-41 0.8 GB: 34-of-41 0.8 GB: 35-of-41 0.8 GB: 36-of-41 0.8 GB: 37-of-41 0.8 GB: 38-of-41 0.8 GB: 39-of-41 0.8 GB: 40-of-41 0.6 GB: 41-of-41
Generates Code	Yes
Model Architecture	GPTBigCodeForCausalLM
License	bigcode-openrail-m
Transformers Version	4.31.0.dev0
Vocabulary Size	49153
Torch Data Type	float16
Activation Function	gelu

Rank the Spider Natsql Wizard Coder Merged 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 Spider Natsql Wizard Coder Merged

Best Alternatives	Context / RAM	Downloads	Likes
WizardCoderSQL 15B V1.0	0K / 31.2 GB	6	1
...r Skeleton Wizard Coder Merged	0K / 31.2 GB	18	13
Minotaur 15B	0K / 31.2 GB	69	15
Minotaur 15B GPTQ	0K / 9.2 GB	6	8

Note: green Score (e.g. "73.2") means that the model is better than richardr1126/spider-natsql-wizard-coder-merged.