What are the hardware requirements for Baguettotron MoE?

Baguettotron MoE requires approximately 26.6 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Baguettotron MoE and how large is it?

Baguettotron MoE is developed by PleIAs, a model with 13.3b 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 Baguettotron MoE?

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

Baguettotron MoE by PleIAs — VRAM 26.6GB, 2K context

Name: Baguettotron MoE
Author: PleIAs

Baguettotron MoE is an open-source language model by PleIAs. Features: 13.3b LLM, VRAM: 26.6GB, Context: 2K, License: apache-2.0.

Arxiv:2609.37891 Baguettotron moe Conversational Custom code Dataset:pleias/synth De En Es Fr It Mixtral Moe Pl Reasoning Region:us Safetensors Synthetic-data

Model Card on HF 🤗: https://huggingface.co/PleIAs/Baguettotron-MoE

Baguettotron MoE Parameters and Internals

LLM Name	Baguettotron MoE
Repository 🤗	https://huggingface.co/PleIAs/Baguettotron-MoE
Model Size	13.3b
Required VRAM	26.6 GB
Updated	2026-10-05
Maintainer	PleIAs
Model Type	baguettotron_moe
Model Files	26.6 GB
Supported Languages	en fr it de es pl
Model Architecture	BaguettotronMoeForCausalLM
License	apache-2.0
Context Length	2048
Model Max Length	2048
Tokenizer Class	PreTrainedTokenizer
Vocabulary Size	65536
Torch Data Type	bfloat16

Rank the Baguettotron MoE 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