What are the hardware requirements for Codellama 2 7B?

Codellama 2 7B requires approximately 13.5 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Codellama 2 7B and how large is it?

Codellama 2 7B is developed by mlabonne, 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 2 7B?

Codellama 2 7B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Codellama 2 7B by mlabonne — VRAM 13.5GB

Name: Codellama 2 7B
Author: mlabonne

Codellama 2 7B is an open-source language model by mlabonne. Features: 7b LLM, VRAM: 13.5GB, License: apache-2.0, Code Generating, LLM Explorer Score: 0.08.

Adapter Base model:adapter:meta-llama/... Base model:meta-llama/llama-2-... Code Codegen Dataset:mlabonne/codellama-2-2... Finetuned Llama Lora Peft Pytorch Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/mlabonne/codellama-2-7b

Codellama 2 7B Parameters and Internals

Model Type

text generation

Training Details

Data Sources:

mlabonne/CodeLlama-2-20k

Methodology:

fine-tuning using QLoRA

Hardware Used:

RTX 3090

LLM Name	Codellama 2 7B
Repository 🤗	https://huggingface.co/mlabonne/codellama-2-7b
Base Model(s)	Llama 2 7B Hf meta-llama/Llama-2-7b-hf
Model Size	7b
Required VRAM	13.5 GB
Updated	2026-08-05
Maintainer	mlabonne
Model Files	0.0 GB 0.0 GB 10.0 GB: 1-of-2 10.0 GB: 1-of-2 3.5 GB: 2-of-2 3.5 GB: 2-of-2 0.0 GB
Generates Code	Yes
Model Architecture	Adapter
License	apache-2.0
Is Biased	none
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	q_proj\|v_proj
LoRA Alpha	16
LoRA Dropout	0.1
R Param	8

Rank the Codellama 2 7B 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 2 7B

Best Alternatives	Context / RAM	Downloads	Likes
Code Llama 7B Chatbot	0K / 1.1 GB	6	0
...10 2024 06 23 10 41 40 3558636	0K / 0.6 GB	5	0
Mistral 7b 2EPOCH DolphinCoder	0K / 0.1 GB	5	0
Mistral 7b 3Epoch DolphinCoder	0K / 0.1 GB	8	0
Codellama2 Finetuned Nl2bash	0K / 0 GB	7	1
Tsql To Plsql	0K / 0.4 GB	5	0
Second Sql Converter Model	0K / 0 GB	8	0
Llama Code 7B	0K / 13.5 GB	6	1
Cria Llama2 7B V1.3 Peft	0K / 0.1 GB	8	0
EvilCodeLlama 7B	0K / 10.8 GB	14	1

Note: green Score (e.g. "73.2") means that the model is better than mlabonne/codellama-2-7b.