What are the hardware requirements for Opencoderplus?

Opencoderplus requires approximately 31.8 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Opencoderplus and how large is it?

Opencoderplus is developed by openchat. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Opencoderplus perform on standard benchmarks?

Opencoderplus has the following published scores: MMLU 42.73. Compare against reference models on this page or on the LLM Explorer leaderboards.

Opencoderplus by openchat — VRAM 31.8GB

Name: Opencoderplus
Author: openchat

Opencoderplus is an open-source language model by openchat. Features: LLM, VRAM: 31.8GB, Code Generating, LLM Explorer Score: 0.11, Arc: 50.6, HellaSwag: 78.2, MMLU: 42.7, GSM8K: 4.6.

Codegen En Endpoints compatible Gpt bigcode Llama Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/openchat/opencoderplus

Opencoderplus Parameters and Internals

Model Type

text generation

Additional Notes

The model requires concatenating tokens in a specific manner as part of the conversation template.

Training Details

Data Sources:

~90K ShareGPT conversations, filtered down to ~6K high-quality conversations

Data Volume:

6K finely-tuned data

Methodology:

Fine-tuning

Context Length:

2048

Model Architecture:

LLaMA-based

Input Output

Input Format:

Concatenation of tokens with specific end-of-turn token.

Accepted Modalities:

text

Output Format:

Tokenized text responses

Performance Tips:

Use bfloat16 for loading pretrained models.

LLM Name	Opencoderplus
Repository 🤗	https://huggingface.co/openchat/opencoderplus
Required VRAM	31.8 GB
Updated	2026-07-22
Maintainer	openchat
Model Type	gpt_bigcode
Model Files	10.0 GB: 1-of-4 9.9 GB: 2-of-4 9.9 GB: 3-of-4 2.0 GB: 4-of-4
Supported Languages	en
Generates Code	Yes
Model Architecture	GPTBigCodeForCausalLM
Transformers Version	4.30.1
Tokenizer Class	GPT2Tokenizer
Beginning of Sentence Token	<\|endoftext\|>
End of Sentence Token	<\|endoftext\|>
Unk Token	<\|endoftext\|>
Vocabulary Size	49153
Torch Data Type	bfloat16
Activation Function	gelu
Errors	replace

Rank the Opencoderplus 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 Opencoderplus

Best Alternatives	Context / RAM	Downloads	Likes
Starcoderbase	0K / 63.3 GB	1144	418
Sqlcoder2	0K / 31.2 GB	4411	117
...rcoder Gpteacher Code Instruct	0K / 63.3 GB	65	80
StarCoder Alpaca	0K / 31 GB	379	1
Sqlcoder	0K / 31.2 GB	223	328
SteloCoder	0K / 31.2 GB	14	1
Minicoder Random	0K / 0.1 GB	10	0
Minicoder Lua	0K / 0.1 GB	8	0
Tiny Starcoder Py	0K / GB	206	2
DPO Santacoder1b	0K / 2.2 GB	9	0

Note: green Score (e.g. "73.2") means that the model is better than openchat/opencoderplus.