What are the hardware requirements for CodeLlama 13B Instruct Hf?

CodeLlama 13B Instruct 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 Instruct Hf and how large is it?

CodeLlama 13B Instruct Hf is developed by codellama, a model with 13b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does CodeLlama 13B Instruct Hf perform on standard benchmarks?

CodeLlama 13B Instruct Hf has the following published scores: MMLU 38.89, HumanEval (Python) 50.6. Compare against reference models on this page or on the LLM Explorer leaderboards.

CodeLlama 13B Instruct Hf by codellama — VRAM 26GB, 16K context

Name: CodeLlama 13B Instruct Hf
Author: codellama

CodeLlama 13B Instruct Hf is an open-source language model by codellama. Features: 13b LLM, VRAM: 26GB, Context: 16K, License: llama2, Instruction-Based, Code Generating, LLM Explorer Score: 0.16, Arc: 44.5, HellaSwag: 64.9, MMLU: 38.9, GSM8K: 12.7, HumanEval: 50.6.

Arxiv:2308.12950 Code Codegen Conversational Deploy:azure Endpoints compatible Instruct Llama Llama2 Pytorch Region:us Safetensors Sharded Tensorflow

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

CodeLlama 13B Instruct Hf Parameters and Internals

Model Type

generative, text-generation

Use Cases

Areas:

Commercial, Research

Applications:

Code synthesis, Code understanding, Code assistant and generation applications

Primary Use Cases:

General code synthesis, Python programming, Instruction following

Limitations:

Output in languages other than English is not recommended., Use in any manner that violates applicable laws or regulations is prohibited.

Considerations:

Developers should perform safety testing and tuning tailored to their specific applications.

Additional Notes

This is a static model trained on an offline dataset.

Supported Languages

primary_language (English), specialties (Programming languages, primarily Python)

Training Details

Data Sources:

Same data as Llama 2

Methodology:

Trained with custom libraries on Meta’s Research Super Cluster

Hardware Used:

A100-80GB GPUs

Model Architecture:

Auto-regressive language model using an optimized transformer architecture

Input Output

Input Format:

Text

Accepted Modalities:

Text

Output Format:

Text

LLM Name	CodeLlama 13B Instruct Hf
Repository 🤗	https://huggingface.co/codellama/CodeLlama-13b-Instruct-hf
Model Size	13b
Required VRAM	26 GB
Updated	2026-07-04
Maintainer	codellama
Model Type	llama
Instruction-Based	Yes
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 Instruct 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

Quantized Models of the CodeLlama 13B Instruct Hf

Model	Likes	Downloads	VRAM
Codellama 7B Instruct GGUF	1	166	2 GB
Codellama 13B Instruct GGUF	0	28	13 GB
CodeLlama 13B Instruct GGUF	132	3987	5 GB
CodeLlama 13B Instruct GGUF	2	611	5 GB
CodeLlama 13B Instruct AWQ	9	261	7 GB
CodeLlama 13B Instruct GPTQ	39	75	7 GB
CodeLlama 13B Instruct GGML	19	11	5 GB

Best Alternatives to CodeLlama 13B Instruct Hf

Best Alternatives	Context / RAM	Downloads	Likes
NexusRaven V2 13B	16K / 26 GB	105	472
CodeLlama 13B MORepair	16K / 26 GB	9	2
CodeLlama 13B Instruct Hf	16K / 26 GB	369	29
TableLLM 13B	16K / 26 GB	98	34
NexusRaven 13B	16K / 26 GB	37	106
Panda Coder 13B	16K / 26 GB	11	14
... Llama 2 13B Instruct Text2sql	16K / 26 GB	8	28
Gen Sim	16K / 0.3 GB	4	3
CodeLlama 13B Instruct Fp16	16K / 26 GB	137	28
...Llama 13B Instruct Hf 4bit MLX	16K / 7.8 GB	113	3

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