What are the hardware requirements for CodeLlama 13B Hf?

CodeLlama 13B Hf requires approximately 26 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 13B Hf and how large is it?

CodeLlama 13B Hf is developed by meta-llama, a model with 13b 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 13B Hf?

CodeLlama 13B Hf is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

CodeLlama 13B Hf by meta-llama — VRAM 26GB, 16K context

Name: CodeLlama 13B Hf
Author: meta-llama

CodeLlama 13B Hf is an open-source language model by meta-llama. Features: 13b LLM, VRAM: 26GB, Context: 16K, License: llama2, Code Generating, LLM Explorer Score: 0.12.

Arxiv:2308.12950 Code Codegen Endpoints compatible Facebook Llama Llama2 Meta Pytorch Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/meta-llama/CodeLlama-13b-hf

CodeLlama 13B Hf Parameters and Internals

Model Type

Text Generation, Code Synthesis

Use Cases

Areas:

Commercial Use, Research Use

Applications:

Code Synthesis, Understanding Tasks, Code Assistant, Generation Applications

Primary Use Cases:

Python Programming, Code Generation

Limitations:

Only tested in English, Violations of laws, Use in languages other than English

Considerations:

Consider meta's responsible use guide for deployment.

Additional Notes

This is a static model trained on an offline dataset with potential future improvements through community feedback.

Supported Languages

English (Full proficiency)

Training Details

Data Sources:

Llama 2 Data Sources

Data Volume:

Unspecified

Methodology:

Optimized Transformer Architecture

Training Time:

January 2023 to July 2023

Hardware Used:

Meta’s Research Super Cluster, A100-80GB GPUs

Model Architecture:

Auto-regressive Transformer

Responsible Ai Considerations

Fairness:

Not fully assessed; testing conducted primarily in English.

Transparency:

Responsible Use Guide provides some transparency guidelines.

Accountability:

Meta is accountable for the license and guidelines, while developers are responsible for output customization.

Mitigation Strategies:

Safety testing and tuning are recommended for specific applications.

Input Output

Input Format:

Text only

Output Format:

Text only

LLM Name	CodeLlama 13B Hf
Repository 🤗	https://huggingface.co/meta-llama/CodeLlama-13b-hf
Model Size	13b
Required VRAM	26 GB
Updated	2026-08-07
Maintainer	meta-llama
Model Type	llama
Model Files	9.9 GB: 1-of-3 9.9 GB: 2-of-3 6.2 GB: 3-of-3 9.9 GB: 1-of-3 9.9 GB: 2-of-3 6.5 GB: 3-of-3
Supported Languages	code
Generates Code	Yes
Model Architecture	LlamaForCausalLM
License	llama2
Context Length	16384
Model Max Length	16384
Transformers Version	4.32.0.dev0
Tokenizer Class	CodeLlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32016
Torch Data Type	bfloat16

Rank the CodeLlama 13B Hf 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 13B Hf

Best Alternatives	Context / RAM	Downloads	Likes
NexusRaven V2 13B	16K / 26 GB	105	472
CodeLlama 13B Instruct Hf	16K / 26 GB	2469	160
CodeLlama 13B MORepair	16K / 26 GB	9	2
CodeLlama 13B Hf	16K / 26 GB	3466	117
Tora Code 13B V1.0	16K / 26 GB	878	15
CodeLlama 13B Python Hf	16K / 26 GB	558	51
...ma 13B Hf Truncated Embeddings	16K / 52.3 GB	5	0
...ma Airoboros Orca Platypus 13B	16K / 26 GB	117	0
Codellama 13B Oasst Sft V10	16K / 25.9 GB	184	70
CodeLlama 13B Hf	16K / 26 GB	224	0

Note: green Score (e.g. "73.2") means that the model is better than meta-llama/CodeLlama-13b-hf.