What are the hardware requirements for CodeLlama 7B Instruct GGML?

CodeLlama 7B Instruct GGML requires approximately 3 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed CodeLlama 7B Instruct GGML and how large is it?

CodeLlama 7B Instruct GGML 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 Instruct GGML?

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

CodeLlama 7B Instruct GGML by TheBloke — VRAM 3GB

Name: CodeLlama 7B Instruct GGML
Author: TheBloke

CodeLlama 7B Instruct GGML is an open-source language model by TheBloke. Features: 7b LLM, VRAM: 3GB, License: llama2, Quantized, Instruction-Based, Code Generating, LLM Explorer Score: 0.08.

Arxiv:2308.12950 Code Codegen Ggml Instruct Llama Llama2 Quantized Region:us

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

CodeLlama 7B Instruct GGML Parameters and Internals

Model Type

llama

Use Cases

Areas:

Commercial, Research

Limitations:

Tested only in English and relevant programming languages, Potential for inaccurate or objectionable responses

Considerations:

Use should comply with applicable laws and not violate ethical guidelines.

Additional Notes

The model is static and trained on an offline dataset. Future versions will enhance safety with community feedback.

Supported Languages

languages (English and relevant programming languages), proficiency ()

Training Details

Hardware Used:

A100-80GB GPUs

Model Architecture:

Optimized transformer architecture

Safety Evaluation

Ethical Considerations:

Code Llama and its variants are a new technology that carries risks with use. As with all LLMs, the potential outputs cannot be predicted in advance, and the model may produce inaccurate or objectionable responses to user prompts.

Responsible Ai Considerations

Mitigation Strategies:

Safety testing and tuning should be performed before deploying any applications of Code Llama.

Input Output

Input Format:

Text input

Output Format:

Text output

LLM Name	CodeLlama 7B Instruct GGML
Repository 🤗	https://huggingface.co/TheBloke/CodeLlama-7B-Instruct-GGML
Model Name	CodeLlama 7B Instruct
Model Creator	Meta
Base Model(s)	codellama/CodeLlama-7b-instruct-hf codellama/CodeLlama-7b-instruct-hf
Model Size	7b
Required VRAM	3 GB
Updated	2026-08-05
Maintainer	TheBloke
Model Type	llama
Instruction-Based	Yes
Model Files	3.0 GB 3.8 GB 3.5 GB 3.1 GB 3.8 GB 4.2 GB 4.2 GB 4.0 GB 4.6 GB 5.1 GB 4.9 GB 4.8 GB 5.7 GB 7.2 GB
Supported Languages	code
GGML Quantization	Yes
Quantization Type	ggml
Generates Code	Yes
Model Architecture	AutoModel
License	llama2

Rank the CodeLlama 7B Instruct 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 CodeLlama 7B Instruct GGML

Best Alternatives	Context / RAM	Downloads	Likes
Oveu 1.1 8B	0K / 0.3 GB	42	1
Personalcoder Dsa V0.1	0K / 0.2 GB	19	1
...86B 8feb Ee84fab5469d 5GU4Xkd3	0K / 1.3 GB	40	0
...29B 92a1 E78acf5901b2 5FWLwQ2G	0K / 1.3 GB	31	0
...29B 92a1 E78acf5901b2 5EEaxgnm	0K / 1.3 GB	28	0
...321 Ac7f 1a661b3375e2 5FjDsFGA	0K / 0.6 GB	27	0
...b1a 9d60 21e6c2d9bdb6 5EeLcV3L	0K / 1.3 GB	25	0
...86B 8feb Ee84fab5469d 5GpcTKW7	0K / 1.3 GB	22	0
...878 Be95 Abe659214b13 5FRdgPRd	0K / 1.3 GB	23	0
...6b7 A781 B99109198970 5G1iwMve	0K / 0.6 GB	22	0

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