What are the hardware requirements for CodeLlama 7B GPTQ?

CodeLlama 7B GPTQ requires approximately 3.9 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 CodeLlama 7B GPTQ and how large is it?

CodeLlama 7B GPTQ is developed by TheBloke, 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 CodeLlama 7B GPTQ?

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

CodeLlama 7B GPTQ by TheBloke — VRAM 3.9GB, 16K context

Name: CodeLlama 7B GPTQ
Author: TheBloke

CodeLlama 7B GPTQ is an open-source language model by TheBloke. Features: 7b LLM, VRAM: 3.9GB, Context: 16K, License: llama2, Quantized, Code Generating, LLM Explorer Score: 0.08.

Arxiv:2308.12950 4-bit Base model:codellama/codellama... Base model:quantized:codellama... Code Codegen Custom code Gptq Llama Llama2 Quantized Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/TheBloke/CodeLlama-7B-GPTQ

CodeLlama 7B GPTQ Parameters and Internals

Model Type

text generation, code synthesis

Use Cases

Areas:

Commercial use, Research use, Code synthesis

Applications:

Code assistant and generation, Python programming handling

Primary Use Cases:

Code generation, Code completion

Considerations:

Safety testing is advised before deployment

Additional Notes

Variants exist for different parameter sizes and purposes.

Supported Languages

English (Proficient), Python (Highly proficient)

Training Details

Data Sources:

Similar data as Llama 2

Data Volume:

Not specified

Methodology:

Optimized transformer architecture

Training Time:

Between January 2023 and July 2023

Hardware Used:

Meta’s Research Super Cluster

Model Architecture:

Auto-regressive language model

Safety Evaluation

Ethical Considerations:

Testing conducted in English; outputs cannot be predicted in advance.

Responsible Ai Considerations

Fairness:

Not specified

Transparency:

Please see the Responsible Use Guide available online

Accountability:

Developers are advised to perform safety testing and tuning

Mitigation Strategies:

Developers are advised to adapt the model for specific applications

Input Output

Input Format:

Text input

Accepted Modalities:

text

Output Format:

Text output

LLM Name	CodeLlama 7B GPTQ
Repository 🤗	https://huggingface.co/TheBloke/CodeLlama-7B-GPTQ
Model Name	CodeLlama 7B
Model Creator	Meta
Base Model(s)	CodeLlama 7B Hf codellama/CodeLlama-7b-hf
Model Size	7b
Required VRAM	3.9 GB
Updated	2026-08-07
Maintainer	TheBloke
Model Type	llama
Model Files	3.9 GB
Supported Languages	code
GPTQ Quantization	Yes
Quantization Type	gptq
Generates Code	Yes
Model Architecture	LlamaForCausalLM
License	llama2
Context Length	16384
Model Max Length	16384
Transformers Version	4.32.0
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32016
Torch Data Type	float16

Rank the CodeLlama 7B GPTQ 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 CodeLlama 7B GPTQ

Best Alternatives	Context / RAM	Downloads	Likes
Codebear 7B 4bit	16K / 3.9 GB	4	1
...a 7B Instruct GPTQ Calib Ja 1K	16K / 3.9 GB	6	0
CodeLlama 7B Instruct GPTQ	16K / 3.9 GB	499	46
CodeLlama 7B Python GPTQ	16K / 3.9 GB	46	24
Codegen Int4 GPTQ Python Code	4K / 3.9 GB	7	0
Llama 2 Coder 7B GPTQ	4K / 3.9 GB	33	10
CodeLlama 7B Java 16bit	16K / 13.5 GB	10	0
Codellama 7B Bnb 4bit	16K / 3.9 GB	3695	9
...ruct Solidity Bnb 4bit Smashed	16K / 4.2 GB	6	0
...lama 7B Tofuagent Contpretrain	16K / 13.5 GB	6	0

Note: green Score (e.g. "73.2") means that the model is better than TheBloke/CodeLlama-7B-GPTQ.