What are the hardware requirements for Codegen 16B Mono Toolbench?

Codegen 16B Mono Toolbench requires approximately 128.4 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Codegen 16B Mono Toolbench and how large is it?

Codegen 16B Mono Toolbench is developed by sambanovasystems, 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 Mono Toolbench?

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

Codegen 16B Mono Toolbench by sambanovasystems — VRAM 128.4GB

Name: Codegen 16B Mono Toolbench
Author: sambanovasystems

Codegen 16B Mono Toolbench is an open-source language model by sambanovasystems. Features: 16b LLM, VRAM: 128.4GB, License: bsd-3-clause, Code Generating, LLM Explorer Score: 0.07.

Arxiv:2203.13474 Arxiv:2305.16504 Codegen Endpoints compatible Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/sambanovasystems/codegen-16B-mono-toolbench

Codegen 16B Mono Toolbench Parameters and Internals

Model Type

Language Model

Use Cases

Areas:

Commercial use, Research use

Limitations:

Should not be used for purposes other than API-based action generation

Additional Notes

This model is instruction tuned for API-based action generation.

Supported Languages

English (Proficient)

Training Details

Data Sources:

API based action generation datasets

Data Volume:

9704 training samples

Methodology:

Instruction tuning

Hardware Used:

4 80GB A100 GPUs

LLM Name	Codegen 16B Mono Toolbench
Repository 🤗	https://huggingface.co/sambanovasystems/codegen-16B-mono-toolbench
Model Size	16b
Required VRAM	128.4 GB
Updated	2026-08-06
Maintainer	sambanovasystems
Model Type	codegen
Model Files	32.1 GB: 1-of-4 32.1 GB: 2-of-4 32.1 GB: 3-of-4 32.1 GB: 4-of-4
Generates Code	Yes
Model Architecture	CodeGenForCausalLM
License	bsd-3-clause
Model Max Length	2048
Transformers Version	4.28.1
Tokenizer Class	GPT2Tokenizer
Vocabulary Size	51200
Torch Data Type	float16
Activation Function	gelu_new

Rank the Codegen 16B Mono Toolbench 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 Mono Toolbench

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 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

Note: green Score (e.g. "73.2") means that the model is better than sambanovasystems/codegen-16B-mono-toolbench.