What are the hardware requirements for Codegen2 16B P?

Codegen2 16B P requires approximately 64.3 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Codegen2 16B P and how large is it?

Codegen2 16B P is developed by Salesforce, a model with 16b 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 Codegen2 16B P?

Codegen2 16B P is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Codegen2 16B P by Salesforce — VRAM 64.3GB

Name: Codegen2 16B P
Author: Salesforce

Codegen2 16B P is an open-source language model by Salesforce. Features: 16b LLM, VRAM: 64.3GB, License: apache-2.0, Code Generating, LLM Explorer Score: 0.08.

Arxiv:2305.02309 Codegen Custom code Endpoints compatible Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/Salesforce/codegen2-16B_P

Codegen2 16B P Parameters and Internals

Model Type

autoregressive, language model, program synthesis

Use Cases

Areas:

program synthesis

Applications:

generating executable code

Primary Use Cases:

Generating executables from English prompts, Completing partially-generated code

Supported Languages

c (supported), c++ (supported), c-sharp (supported), dart (supported), go (supported), java (supported), javascript (supported), kotlin (supported), lua (supported), php (supported), python (supported), ruby (supported), rust (supported), scala (supported), shell (supported), sql (supported), swift (supported), typescript (supported), vue (supported)

Training Details

Data Sources:

the deduplicated version of the Stack dataset (v1.1)

Methodology:

cross-entropy loss to maximize the likelihood of sequential inputs

Input Output

Accepted Modalities:

text

LLM Name	Codegen2 16B P
Repository 🤗	https://huggingface.co/Salesforce/codegen2-16B_P
Model Size	16b
Required VRAM	64.3 GB
Updated	2026-06-30
Maintainer	Salesforce
Model Type	codegen
Model Files	9.7 GB: 1-of-7 9.7 GB: 2-of-7 9.7 GB: 3-of-7 9.7 GB: 4-of-7 9.7 GB: 5-of-7 9.7 GB: 6-of-7 6.1 GB: 7-of-7
Generates Code	Yes
Model Architecture	CodeGenForCausalLM
License	apache-2.0
Model Max Length	1024
Transformers Version	4.25.1
Tokenizer Class	GPT2Tokenizer
Vocabulary Size	51200
Torch Data Type	float32
Activation Function	gelu_new

Rank the Codegen2 16B 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 Codegen2 16B P

Best Alternatives	Context / RAM	Downloads	Likes
Instruct Codegen 16B	0K / 32.2 GB	8	21
Codegen 16B Mono Toolbench	0K / 128.4 GB	7	5
Codegen 16B Multi 6 Parts	0K / 32.2 GB	12	0
Codegen 16B Nl Sharded	0K / 32.1 GB	24	7
Codegen 16B Nl	0K / 32.2 GB	689	18
Fine Tuned Codegen 16B Verilog	0K / 32.2 GB	33	15
Codegen 16B Multi	0K / 32.2 GB	148	119
Codegen 16B Mono	0K / 32.2 GB	89	126