What are the hardware requirements for Codegen 2B Multi?

Codegen 2B Multi requires approximately 5.7 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Codegen 2B Multi and how large is it?

Codegen 2B Multi is developed by Salesforce, a model with 2b 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 Codegen 2B Multi?

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

Codegen 2B Multi by Salesforce — VRAM 5.7GB

Name: Codegen 2B Multi
Author: Salesforce

Codegen 2B Multi is an open-source language model by Salesforce. Features: 2b LLM, VRAM: 5.7GB, License: bsd-3-clause, Code Generating, LLM Explorer Score: 0.01.

Arxiv:2203.13474 Codegen Deploy:azure Endpoints compatible Pytorch Region:us

Model Card on HF 🤗: https://huggingface.co/Salesforce/codegen-2B-multi

Codegen 2B Multi Parameters and Internals

Model Type

text generation, program synthesis

Use Cases

Areas:

research, commercial applications

Applications:

program synthesis, code generation

Primary Use Cases:

Generating executable code from English prompts, Completing partially generated code

Limitations:

Only best at program synthesis tasks

Considerations:

Prompts should be in the form of a comment string

Supported Languages

Python (High), C (High), C++ (High), Go (High), Java (High), JavaScript (High)

Training Details

Data Sources:

BigQuery, GitHub repositories

Data Volume:

119.2B tokens

Methodology:

Cross-entropy loss to maximize likelihood of sequential inputs

Hardware Used:

TPU-v4-512

Model Architecture:

Autoregressive language model

LLM Name	Codegen 2B Multi
Repository 🤗	https://huggingface.co/Salesforce/codegen-2B-multi
Model Size	2b
Required VRAM	5.7 GB
Updated	2026-07-11
Maintainer	Salesforce
Model Type	codegen
Model Files	5.7 GB
Generates Code	Yes
Model Architecture	CodeGenForCausalLM
License	bsd-3-clause
Model Max Length	2048
Transformers Version	4.21.0.dev0
Tokenizer Class	GPT2Tokenizer
Vocabulary Size	51200
Torch Data Type	float16
Activation Function	gelu_new

Rank the Codegen 2B Multi 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 Codegen 2B Multi

Best Alternatives	Context / RAM	Downloads	Likes
Archgen 2B V1	0K / 5.6 GB	7	0
...Python 18K Alpaca Full Dataset	0K / 5.6 GB	6	0
Salesforce Codegen 2B Multi Ov	0K / 11.1 GB	7	0
Nsql 2B	0K / 11.3 GB	15	9
Instruct Codegen 2B Multi	0K / 11.3 GB	10	1
Diff Codegen 2B V2	0K / 5.7 GB	26	6
...en 2B Mono Instruct Py Revised	0K / 11.3 GB	7	1
Codegen 2B Mono Xlcost	0K / 5.7 GB	6	1
Codegen 2B Multi Xlcost	0K / 5.7 GB	112	1
Fine Tuned Codegen 2B Verilog	0K / 11.3 GB	106	8

Note: green Score (e.g. "73.2") means that the model is better than Salesforce/codegen-2B-multi.