What are the hardware requirements for Codet5p 220M Py Ct2 Int8?

Codet5p 220M Py Ct2 Int8 requires approximately 0.2 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Codet5p 220M Py Ct2 Int8 and how large is it?

Codet5p 220M Py Ct2 Int8 is developed by jncraton, a model with 220m 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 Codet5p 220M Py Ct2 Int8?

Codet5p 220M Py Ct2 Int8 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Codet5p 220M Py Ct2 Int8 by jncraton — VRAM 0.2GB

Name: Codet5p 220M Py Ct2 Int8
Author: jncraton

Codet5p 220M Py Ct2 Int8 is an open-source language model by jncraton. Features: 220m LLM, VRAM: 0.2GB, License: bsd-3-clause, LLM Explorer Score: 0.07.

Arxiv:2305.07922 Endpoints compatible Region:us

Model Card on HF 🤗: https://huggingface.co/jncraton/codet5p-220m-py-ct2-int8

Codet5p 220M Py Ct2 Int8 Parameters and Internals

Model Type

encoder-decoder

Use Cases

Areas:

code understanding, code generation

Applications:

text-to-code generation, code completion, code retrieval

Additional Notes

The model is instruction-tuned following Code Alpaca to align with natural language instructions.

Supported Languages

c (supported), c++ (supported), c-sharp (supported), go (supported), java (supported), javascript (supported), php (supported), python (supported), ruby (supported)

Training Details

Data Sources:

github-code dataset (permissively licensed code)

Methodology:

Multilingual unimodal code pretraining followed by Python subset fine-tuning with causal language modeling.

Model Architecture:

Shallow encoder and deep decoder architecture.

Input Output

Input Format:

Python functions

Accepted Modalities:

text

Output Format:

Generated code

LLM Name	Codet5p 220M Py Ct2 Int8
Repository 🤗	https://huggingface.co/jncraton/codet5p-220m-py-ct2-int8
Model Size	220m
Required VRAM	0.2 GB
Updated	2026-07-31
Maintainer	jncraton
Model Files	0.2 GB
Model Architecture	AutoModel
License	bsd-3-clause
Model Max Length	512
Tokenizer Class	RobertaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Errors	replace

Rank the Codet5p 220M Py Ct2 Int8 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 Codet5p 220M Py Ct2 Int8

Best Alternatives	Context / RAM	Downloads	Likes
Saily 220B GGUF	0K / GB	7	9

Note: green Score (e.g. "73.2") means that the model is better than jncraton/codet5p-220m-py-ct2-int8.