What are the hardware requirements for Rubicon Preview?

Rubicon Preview requires approximately 61.1 GB of VRAM and supports a context window of 40K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Rubicon Preview and how large is it?

Rubicon Preview is developed by inclusionAI, a model with 30.5b 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 Rubicon Preview?

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

Rubicon Preview by inclusionAI — VRAM 61.1GB, 40K context

Name: Rubicon Preview
Author: inclusionAI

Rubicon Preview is an open-source language model by inclusionAI. Features: 30.5b LLM, VRAM: 61.1GB, Context: 40K, License: apache-2.0, LLM Explorer Score: 0.2.

Arxiv:2508.12790 Conversational Deploy:azure Endpoints compatible Qwen3 moe Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/inclusionAI/Rubicon-Preview

Rubicon Preview Parameters and Internals

LLM Name	Rubicon Preview
Repository 🤗	https://huggingface.co/inclusionAI/Rubicon-Preview
Model Size	30.5b
Required VRAM	61.1 GB
Updated	2026-07-09
Maintainer	inclusionAI
Model Type	qwen3_moe
Model Files	5.0 GB: 1-of-13 5.0 GB: 2-of-13 5.0 GB: 3-of-13 5.0 GB: 4-of-13 5.0 GB: 5-of-13 5.0 GB: 6-of-13 5.0 GB: 7-of-13 5.0 GB: 8-of-13 5.0 GB: 9-of-13 5.0 GB: 10-of-13 5.0 GB: 11-of-13 5.0 GB: 12-of-13 1.1 GB: 13-of-13
Model Architecture	Qwen3MoeForCausalLM
License	apache-2.0
Context Length	40960
Model Max Length	40960
Transformers Version	4.51.3
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Torch Data Type	bfloat16
Errors	replace

Rank the Rubicon Preview 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 Rubicon Preview

Best Alternatives	Context / RAM	Downloads	Likes
SU 01	256K / 61.1 GB	199	28
SimpleChat 30BA3B V2	195K / 61.1 GB	15	5
SimpleChat 30BA3B V1	39K / 61.1 GB	7	1
MiroThinker 1.7 Mini Mlx 4Bit	256K / 17.2 GB	37	2

Note: green Score (e.g. "73.2") means that the model is better than inclusionAI/Rubicon-Preview.