What are the hardware requirements for Codegen 16B Nl Sharded?

Codegen 16B Nl Sharded requires approximately 32.1 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Codegen 16B Nl Sharded and how large is it?

Codegen 16B Nl Sharded is developed by abacaj, 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 Codegen 16B Nl Sharded?

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

Codegen 16B Nl Sharded by abacaj — VRAM 32.1GB

Name: Codegen 16B Nl Sharded
Author: abacaj

Codegen 16B Nl Sharded is an open-source language model by abacaj. Features: 16b LLM, VRAM: 32.1GB, License: bsd-3-clause, Code Generating, LLM Explorer Score: 0.06.

Arxiv:2203.13474 Codegen Endpoints compatible Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/abacaj/codegen-16B-nl-sharded

Codegen 16B Nl Sharded Parameters and Internals

Model Type

autoregressive

Use Cases

Areas:

Program Synthesis

Applications:

Code generation benchmarks such as HumanEval and MTPB

Primary Use Cases:

Generating executable code from English prompts

Limitations:

It is not optimal for tasks outside program synthesis.

Additional Notes

Sharded version using torch.float16.

Supported Languages

English (high), Programming Languages (high)

Training Details

Data Sources:

the Pile by EleutherAI

Methodology:

Cross-entropy loss to maximize likelihood of sequential inputs.

Hardware Used:

TPU-v4-512 by Google

Model Architecture:

Autoregressive Language Model

LLM Name	Codegen 16B Nl Sharded
Repository 🤗	https://huggingface.co/abacaj/codegen-16B-nl-sharded
Model Size	16b
Required VRAM	32.1 GB
Updated	2026-07-16
Maintainer	abacaj
Model Type	codegen
Model Files	4.0 GB: 1-of-9 4.0 GB: 2-of-9 3.9 GB: 3-of-9 3.9 GB: 4-of-9 4.0 GB: 5-of-9 3.9 GB: 6-of-9 3.9 GB: 7-of-9 3.9 GB: 8-of-9 0.6 GB: 9-of-9
Generates Code	Yes
Model Architecture	CodeGenForCausalLM
License	bsd-3-clause
Model Max Length	2048
Transformers Version	4.26.1
Tokenizer Class	GPT2Tokenizer
Vocabulary Size	51200
Torch Data Type	float16
Activation Function	gelu_new

Rank the Codegen 16B Nl Sharded 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 16B Nl Sharded

Best Alternatives	Context / RAM	Downloads	Likes
Codegen2 16B P	0K / 64.3 GB	1290	45
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	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

Note: green Score (e.g. "73.2") means that the model is better than abacaj/codegen-16B-nl-sharded.