What are the hardware requirements for AREX 2 OQ8e?

AREX 2 OQ8e requires approximately 29.4 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed AREX 2 OQ8e and how large is it?

AREX 2 OQ8e is developed by a-gordo, a model with 27.4b 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 AREX 2 OQ8e?

AREX 2 OQ8e is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

AREX 2 OQ8e by a-gordo — VRAM 29.4GB

Name: AREX 2 OQ8e
Author: a-gordo

AREX 2 OQ8e is an open-source language model by a-gordo. Features: 27.4b LLM, VRAM: 29.4GB, License: apache-2.0, LLM Explorer Score: 0.29.

Arxiv:2609.38288 8-bit Base model:baai/arex-2 Base model:quantized:baai/arex... Conversational Image-text-to-text Mlx Omlx Oq8e Quantized Qwen3 5 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/a-gordo/AREX-2-oQ8e

AREX 2 OQ8e Parameters and Internals

LLM Name	AREX 2 OQ8e
Repository 🤗	https://huggingface.co/a-gordo/AREX-2-oQ8e
Base Model(s)	AREX 2 BAAI/AREX-2
Model Size	27.4b
Required VRAM	29.4 GB
Updated	2026-10-30
Maintainer	a-gordo
Model Type	qwen3_5
Model Files	5.0 GB: 1-of-6 5.0 GB: 2-of-6 5.0 GB: 3-of-6 5.0 GB: 4-of-6 5.0 GB: 5-of-6 4.4 GB: 6-of-6
Model Architecture	Qwen3_5ForConditionalGeneration
License	apache-2.0
Model Max Length	262144
Transformers Version	5.2.0
Tokenizer Class	TokenizersBackend
Padding Token	<\|endoftext\|>
Errors	replace

Rank the AREX 2 OQ8e 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 AREX 2 OQ8e

Best Alternatives	Context / RAM	Downloads	Likes
TelecomGPT R1	16K / 54.7 GB	365	29
Openjev	0K / 54.7 GB	5073	108
Clef OQ4e	0K / 16.6 GB	309	9
JAX XORTRON	0K / 54.7 GB	444	1
Nesi1	0K / 0.8 GB	109	2
Clef FP8	0K / 35.9 GB	85	2
Clef NVFP4	0K / 19.7 GB	62	2
AREX 2 FP8	0K / 35.9 GB	32	3
Hemmingway 1 Heretic	0K / 54.7 GB	36	0
Agent.Xortron	0K / 54.7 GB	26	2

Note: green Score (e.g. "73.2") means that the model is better than a-gordo/AREX-2-oQ8e.