What are the hardware requirements for Octogeex?

Octogeex requires approximately 12.5 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Octogeex and how large is it?

Octogeex is developed by bigcode, a model with 6b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Octogeex perform on standard benchmarks?

Octogeex has the following published scores: HumanEval (Python) 42.28. Compare against reference models on this page or on the LLM Explorer leaderboards.

Octogeex by bigcode — VRAM 12.5GB

Name: Octogeex
Author: bigcode

Octogeex is an open-source language model by bigcode. Features: 6b LLM, VRAM: 12.5GB, LLM Explorer Score: 0.08, HumanEval: 42.3.

Arxiv:2308.07124 Chatglm Codegeex Custom code Dataset:bigcode/commitpackft Dataset:bigcode/oasst-octopack En Endpoints compatible Glm Model-index Pytorch Region:us Zh

Model Card on HF 🤗: https://huggingface.co/bigcode/octogeex

Octogeex Parameters and Internals

Model Type

text-generation, code-writing

Use Cases

Areas:

research, commercial applications

Primary Use Cases:

instruction following in code generation

Limitations:

known limitations or unsuitable use cases not specified

Training Details

Data Sources:

CommitPackFT, OASST

Data Volume:

1 trillion pretraining & 2M instruction tuning tokens

Methodology:

instruction tuning

Training Time:

24 days

Hardware Used:

512 Tesla A100 GPUs

Model Architecture:

GPT-2 model with multi-query attention and Fill-in-the-Middle objective

Input Output

Input Format:

Instructions prefixed with 'Question: ' and suffixed with 'Answer:'

Accepted Modalities:

text

Output Format:

Text generated for code tasks.

Performance Tips:

Preface input with correct format for optimal results.

LLM Name	Octogeex
Repository 🤗	https://huggingface.co/bigcode/octogeex
Model Size	6b
Required VRAM	12.5 GB
Updated	2026-08-03
Maintainer	bigcode
Model Type	chatglm
Model Files	12.5 GB
Supported Languages	zh en
Model Architecture	ChatGLMModel
Transformers Version	4.30.2
Tokenizer Class	ChatGLMTokenizer
Torch Data Type	bfloat16

Rank the Octogeex 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 Octogeex

Best Alternatives	Context / RAM	Downloads	Likes
Chatglm3 6B	0K / 12.5 GB	659154	1138
Chatglm2 6B	0K / 12.5 GB	617325	2050
Chatglm2 6B	0K / 12.5 GB	447665	2057
Chatglm3 6B	0K / 12.5 GB	87714	1166
Chatglm 6B	0K / 13.5 GB	1297	2903
Chatglm 6B	0K / 13.5 GB	2816	2862
Codegeex2 6B	0K / 12.5 GB	435	258
Codegeex2 6B	0K / 12.5 GB	119	256

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