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

Codegen25 7B Mono 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 Mono P and how large is it?

Codegen25 7B Mono 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 Mono P?

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

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

Name: Codegen25 7B Mono P
Author: Salesforce

Codegen25 7B Mono 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-mono_P

Codegen25 7B Mono P Parameters and Internals

Model Type

autoregressive, program synthesis

Use Cases

Areas:

program synthesis

Considerations:

The model generates executable code, and users should ensure proper use to avoid generating potentially harmful code.

Additional Notes

The model was pre-filtered for permissive licenses but may generate verbatim code from the dataset which requires appropriate attribution.

Supported Languages

Code ()

Training Details

Data Sources:

bigcode/starcoderdata, Python

Data Volume:

1.4T tokens

Methodology:

Autoregressive training with infilling and instruction data

Input Output

Input Format:

Text with CodeGen2 format for infilling

Accepted Modalities:

text

Output Format:

Generated text

Performance Tips:

Use infilling tokens appropriately for desired output.

LLM Name	Codegen25 7B Mono P
Repository 🤗	https://huggingface.co/Salesforce/codegen25-7b-mono_P
Model Size	7b
Required VRAM	27.6 GB
Updated	2026-07-22
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 Mono 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

Quantized Models of the Codegen25 7B Mono P

Model	Likes	Downloads	VRAM
Codegen25 7B Mono GPTQ	8	8	4 GB

Best Alternatives to Codegen25 7B Mono 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-mono_P.