What are the hardware requirements for WizardCoder 15B 1.0 GGML?

WizardCoder 15B 1.0 GGML requires approximately 10.7 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed WizardCoder 15B 1.0 GGML and how large is it?

WizardCoder 15B 1.0 GGML is developed by TheBloke, 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 WizardCoder 15B 1.0 GGML?

WizardCoder 15B 1.0 GGML is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

WizardCoder 15B 1.0 GGML by TheBloke — VRAM 10.7GB

Name: WizardCoder 15B 1.0 GGML
Author: TheBloke

WizardCoder 15B 1.0 GGML is an open-source language model by TheBloke. Features: 15b LLM, VRAM: 10.7GB, License: bigcode-openrail-m, Quantized, LLM Explorer Score: 0.07.

Ggml Quantized Region:us Starcoder

Model Card on HF 🤗: https://huggingface.co/TheBloke/WizardCoder-15B-1.0-GGML

WizardCoder 15B 1.0 GGML Parameters and Internals

Model Type

code LLM

Use Cases

Areas:

research, coding tasks

Applications:

code generation, software development, programming assistance

Primary Use Cases:

writing and completing code-related tasks

Limitations:

Primarily focused on English coding instructions

Additional Notes

The model is fine-tuned from StarCoder with modified hyperparameters.

Supported Languages

programming_languages (Python, Java, etc. (code-related instructions))

Training Details

Data Sources:

code instruction data

Data Volume:

78k evolved code instructions

Methodology:

Utilizing the Evol-Instruct method

Context Length:

2048

Model Architecture:

LLM with Evol-Instruct adaptation for coding tasks

Input Output

Input Format:

Customized prompt for code-related tasks.

Accepted Modalities:

text

Output Format:

text

LLM Name	WizardCoder 15B 1.0 GGML
Repository 🤗	https://huggingface.co/TheBloke/WizardCoder-15B-1.0-GGML
Base Model(s)	...ider Natsql Wizard Coder Qlora richardr1126/spider-natsql-wizard-coder-qlora
Model Size	15b
Required VRAM	10.7 GB
Updated	2026-07-04
Maintainer	TheBloke
Model Type	starcoder
Model Files	10.7 GB 11.9 GB 13.1 GB 14.3 GB 20.1 GB
GGML Quantization	Yes
Quantization Type	ggml
Model Architecture	AutoModel
License	bigcode-openrail-m

Rank the WizardCoder 15B 1.0 GGML 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 WizardCoder 15B 1.0 GGML

Best Alternatives	Context / RAM	Downloads	Likes
Ct2fast WizardCoder 15B V1.0	0K / 15.6 GB	6	6