What are the hardware requirements for Gogpt 3B Bloom?

Gogpt 3B Bloom requires approximately 14.6 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Gogpt 3B Bloom and how large is it?

Gogpt 3B Bloom is developed by golaxy, a model with 3b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Gogpt 3B Bloom perform on standard benchmarks?

Gogpt 3B Bloom has the following published scores: MMLU 25.2. Compare against reference models on this page or on the LLM Explorer leaderboards.

Gogpt 3B Bloom by golaxy — VRAM 14.6GB

Name: Gogpt 3B Bloom
Author: golaxy

Gogpt 3B Bloom is an open-source language model by golaxy. Features: 3b LLM, VRAM: 14.6GB, License: apache-2.0, LLM Explorer Score: 0.11, Arc: 31.9, HellaSwag: 50.3, MMLU: 25.2, GSM8K: 0.2.

Bloom Dataset:bellegroup/school math... Dataset:bellegroup/train 0.5m ... Dataset:bellegroup/train 1m cn Dataset:bellegroup/train 2m cn Dataset:bellegroup/train 3.5m ... Endpoints compatible Pytorch Region:us Sharded Tensorboard Zh

Model Card on HF 🤗: https://huggingface.co/golaxy/gogpt-3b-bloom

Gogpt 3B Bloom Parameters and Internals

Model Type

text generation

Use Cases

Areas:

research, commercial applications

Additional Notes

Development of GoGPT is ongoing, with future plans to incorporate RLFH training and English-Chinese parallel corpora.

Supported Languages

zh (high)

Training Details

Data Sources:

BelleGroup/train_2M_CN, BelleGroup/train_3.5M_CN, BelleGroup/train_1M_CN, BelleGroup/train_0.5M_CN, BelleGroup/school_math_0.25M

Methodology:

Fine-tuning using diverse Chinese instruction data.

Model Architecture:

BLOOM-based model

LLM Name	Gogpt 3B Bloom
Repository 🤗	https://huggingface.co/golaxy/gogpt-3b-bloom
Model Size	3b
Required VRAM	14.6 GB
Updated	2026-08-07
Maintainer	golaxy
Model Type	bloom
Model Files	9.9 GB: 1-of-2 4.7 GB: 2-of-2 0.0 GB
Supported Languages	zh
Model Architecture	BloomForCausalLM
License	apache-2.0
Model Max Length	2048
Transformers Version	4.29.1
Tokenizer Class	BloomTokenizer
Padding Token	<pad>
Vocabulary Size	250880
Torch Data Type	float32

Rank the Gogpt 3B Bloom 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 Gogpt 3B Bloom

Best Alternatives	Context / RAM	Downloads	Likes
Bloom 3B Conversational	0K / 6.1 GB	118	2
Bloomz 3B Sft Chat	0K / 6 GB	77	12
Blossom V2 3B	0K / 6 GB	77	0
Bloom Zh 3B Chat	0K / 6 GB	1925	11
Blossom V1 3B	0K / 6 GB	82	1
Gpt3 Finnish 3B Instruct	0K / 12.7 GB	4	1
... Bloom 3B Conversational 4bits	0K / 2.6 GB	10	0
Deer 3B	0K / 14.6 GB	63	2
Bloom 3B	0K / 6 GB	17625	94
Bloomz 3B	0K / 6 GB	3680	81

Note: green Score (e.g. "73.2") means that the model is better than golaxy/gogpt-3b-bloom.