What are the hardware requirements for Codegen25 7B Multi P?

Codegen25 7B Multi P requires approximately 27.6 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Codegen25 7B Multi P and how large is it?

Codegen25 7B Multi P is developed by Salesforce, 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 Codegen25 7B Multi P?

Codegen25 7B Multi P is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Codegen25 7B Multi P by Salesforce — VRAM 27.6GB, 2K context

Name: Codegen25 7B Multi P
Author: Salesforce

Codegen25 7B Multi P is an open-source language model by Salesforce. Features: 7b LLM, VRAM: 27.6GB, Context: 2K, License: apache-2.0, LLM Explorer Score: 0.08.

Arxiv:2305.02309 Code Dataset:bigcode/starcoderdata Endpoints compatible Llama Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/Salesforce/codegen25-7b-multi_P

Codegen25 7B Multi P Parameters and Internals

Model Type

autoregressive, language model

Use Cases

Areas:

program synthesis

Applications:

program synthesis, code generation

Primary Use Cases:

Generating executable code given English prompts

Limitations:

Can generate source code verbatim from the dataset

Considerations:

Attribution may be required for generated code

Additional Notes

The model supports both infilling and causal sampling capabilities.

Supported Languages

languages_supported (Multiple programming languages), language_proficiency ()

Training Details

Data Sources:

StarCoderData

Data Volume:

1.4T tokens

Input Output

Input Format:

Natural language and programming language texts

Accepted Modalities:

text

Output Format:

Executable code

Performance Tips:

LLM Name	Codegen25 7B Multi P
Repository 🤗	https://huggingface.co/Salesforce/codegen25-7b-multi_P
Model Size	7b
Required VRAM	27.6 GB
Updated	2026-07-26
Maintainer	Salesforce
Model Type	llama
Model Files	9.9 GB: 1-of-3 10.0 GB: 2-of-3 7.7 GB: 3-of-3
Supported Languages	code
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	2048
Model Max Length	2048
Transformers Version	4.29.2
Tokenizer Class	CodeGen25Tokenizer
Vocabulary Size	51200
Torch Data Type	float32

Rank the Codegen25 7B Multi P 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 Codegen25 7B Multi P

Best Alternatives	Context / RAM	Downloads
124	1024K / 16.1 GB	93
162	1024K / 16.1 GB	60
157	1024K / 16.1 GB	101
118	1024K / 16.1 GB	15
A5.4	1024K / 16.1 GB	12
A3.4	1024K / 16.1 GB	13
A2.4	1024K / 16.1 GB	12
A6 L	1024K / 16.1 GB	201
M	1024K / 16.1 GB	127
2 Very Sci Fi	1024K / 16.1 GB	317

Note: green Score (e.g. "73.2") means that the model is better than Salesforce/codegen25-7b-multi_P.