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

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

Codegen25 7B Instruct 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 Instruct P?

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

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

Name: Codegen25 7B Instruct P
Author: Salesforce

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

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

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

Codegen25 7B Instruct P Parameters and Internals

Model Type

program synthesis, code generation

Use Cases

Areas:

program synthesis

Primary Use Cases:

generating executable code from English prompts, code autocompletion

Limitations:

model can generate verbatim code from dataset

Considerations:

Attribution or other specific requirements might be needed due to source code license.

Additional Notes

The model is more efficient and requires less size than StarCoderBase-15.5B achieving competitive results.

Supported Languages

programming_languages_supported (multiple)

Training Details

Data Sources:

bigcode/starcoderdata

Data Volume:

1.4 trillion tokens

Methodology:

autoregressive language model with instruction tuning

Model Architecture:

autoregressive

Input Output

Input Format:

Comment strings for prompts

Accepted Modalities:

text

Output Format:

Executable code

LLM Name	Codegen25 7B Instruct P
Repository 🤗	https://huggingface.co/Salesforce/codegen25-7b-instruct_P
Model Size	7b
Required VRAM	27.6 GB
Updated	2026-07-07
Maintainer	Salesforce
Model Type	llama
Instruction-Based	Yes
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	other
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 Instruct 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 Instruct P

Best Alternatives	Context / RAM	Downloads	Likes
124	1024K / 16.1 GB	93	0
A5.4	1024K / 16.1 GB	12	0
A3.4	1024K / 16.1 GB	13	0
A2.4	1024K / 16.1 GB	12	0
... Qwen2.5llamaify 7B V23.1 200K	195K / 15.2 GB	29	5
Salamandra 7B Instruct 2606	160K / 15.6 GB	946	2
SuperNeuralDreadDevil 8B	128K / 16.1 GB	14	1
Falcon3 7B Instruct	32K / 14.8 GB	11749	80
Falcon3 Jessi V0.4 7B Slerp	32K / 14.9 GB	34	9
Jessi V0.4 Falcon3 7B Instruct	32K / 14.8 GB	22	0

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