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

CodeLlama 7B Instruct Hf requires approximately 13.5 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 Instruct Hf and how large is it?

CodeLlama 7B Instruct Hf is developed by codellama, a model with 7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does CodeLlama 7B Instruct Hf perform on standard benchmarks?

CodeLlama 7B Instruct Hf has the following published scores: MMLU 34.54, HumanEval (Python) 45.65. Compare against reference models on this page or on the LLM Explorer leaderboards.

CodeLlama 7B Instruct Hf by codellama — VRAM 13.5GB, 16K context

Name: CodeLlama 7B Instruct Hf
Rating: 2 (1 reviews)
Author: codellama

CodeLlama 7B Instruct Hf is an open-source language model by codellama. Features: 7b LLM, VRAM: 13.5GB, Context: 16K, License: llama2, Instruction-Based, Code Generating, LLM Explorer Score: 0.18, Arc: 36.5, HellaSwag: 55.4, MMLU: 34.5, GSM8K: 8, HumanEval: 45.7.

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-7b-Instruct-hf

CodeLlama 7B 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 7B Instruct Hf
Repository 🤗	https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf
Model Size	7b
Required VRAM	13.5 GB
Updated	2026-07-22
Maintainer	codellama
Model Type	llama
Instruction-Based	Yes
Model Files	10.0 GB: 1-of-2 3.5 GB: 2-of-2 4.9 GB: 1-of-3 5.0 GB: 2-of-3 3.6 GB: 3-of-3
Supported Languages	code
Generates Code	Yes
Model Architecture	LlamaForCausalLM
License	llama2
Context Length	16384
Model Max Length	16384
Transformers Version	4.33.0.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 7B 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 7B Instruct Hf

Model	Likes	Downloads	VRAM
...B Instruct Hf Bnb 4bit Smashed	0	6	4 GB

Best Alternatives to CodeLlama 7B Instruct Hf

Best Alternatives	Context / RAM	Downloads	Likes
Deepseek Coder 6.7B Instruct	16K / 13.5 GB	535311	507
GetCode Slerp	16K / 13.6 GB	87	1
Stack Codellama 7B Inst	16K / 13.5 GB	66	0
CodeV CL 7B	16K / 13.5 GB	430	1
CodeLlama 7B Instruct Hf	16K / 13.5 GB	2313	63
Glaive Coder 7B	16K / 27 GB	85	55
...deLlama 7B Instruct Hf 8bits Q	16K / 4.2 GB	17	1
Llama 2 7B Chat Finetune5	16K / 13.8 GB	3	1
...ama 7B Instruct Hf Dequantized	16K / 13.5 GB	197	0
CodeLLama SFT FILTERED	16K / 13.5 GB	9	0

Note: green Score (e.g. "73.2") means that the model is better than codellama/CodeLlama-7b-Instruct-hf.