What are the hardware requirements for Spider Skeleton Wizard Coder 8bit?

Spider Skeleton Wizard Coder 8bit requires approximately 15.9 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Spider Skeleton Wizard Coder 8bit and how large is it?

Spider Skeleton Wizard Coder 8bit is developed by richardr1126. 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 Skeleton Wizard Coder 8bit?

Spider Skeleton Wizard Coder 8bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Spider Skeleton Wizard Coder 8bit by richardr1126 — VRAM 15.9GB

Name: Spider Skeleton Wizard Coder 8bit
Author: richardr1126

Spider Skeleton Wizard Coder 8bit is an open-source language model by richardr1126. Features: LLM, VRAM: 15.9GB, License: bigcode-openrail-m, Quantized, Instruction-Based, Code Generating, Merged, LLM Explorer Score: 0.08.

Merged Model Arxiv:1809.08887 Arxiv:2305.14314 8-bit 8bit Codegen Codegen Dataset:richardr1126/spider-sk... Dataset:spider Endpoints compatible Gpt bigcode Instruct Pytorch Quantized Region:us Sharded Spider Sql Sql Sql finetune

Model Card on HF 🤗: https://huggingface.co/richardr1126/spider-skeleton-wizard-coder-8bit

Spider Skeleton Wizard Coder 8bit Parameters and Internals

Model Type

text-to-SQL

Additional Notes

This is the bitsandbytes 8-bit version of the model. It must be loaded onto a GPU to function.

Training Details

Data Sources:

Spider dataset - https://arxiv.org/abs/1809.08887

Methodology:

Finetuned on Spider context training dataset using QLoRa

Hardware Used:

3x RTX6000 48GB

Input Output

Accepted Modalities:

text

Output Format:

SQL

LLM Name	Spider Skeleton Wizard Coder 8bit
Repository 🤗	https://huggingface.co/richardr1126/spider-skeleton-wizard-coder-8bit
Merged Model	Yes
Required VRAM	15.9 GB
Updated	2026-07-05
Maintainer	richardr1126
Model Type	gpt_bigcode
Instruction-Based	Yes
Model Files	9.9 GB: 1-of-2 6.0 GB: 2-of-2
Quantization Type	8bit
Generates Code	Yes
Model Architecture	GPTBigCodeForCausalLM
License	bigcode-openrail-m
Model Max Length	2048
Transformers Version	4.32.0.dev0
Tokenizer Class	GPT2Tokenizer
Vocabulary Size	49153
Torch Data Type	float16
Activation Function	gelu

Rank the Spider Skeleton Wizard Coder 8bit 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 Skeleton Wizard Coder 8bit

Best Alternatives	Context / RAM	Downloads	Likes
...rcoder Gpteacher Code Instruct	0K / 63.3 GB	65	80

Note: green Score (e.g. "73.2") means that the model is better than richardr1126/spider-skeleton-wizard-coder-8bit.