What are the hardware requirements for Laguna S 2.1 OQ3e?

Laguna S 2.1 OQ3e requires approximately 49 GB of VRAM and supports a context window of 1024K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Laguna S 2.1 OQ3e and how large is it?

Laguna S 2.1 OQ3e is developed by mlx-community, 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 Laguna S 2.1 OQ3e?

Laguna S 2.1 OQ3e is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Laguna S 2.1 OQ3e by mlx-community — VRAM 49GB, 1024K context

Name: Laguna S 2.1 OQ3e
Author: mlx-community

Laguna S 2.1 OQ3e is an open-source language model by mlx-community. Features: 13.3b LLM, VRAM: 49GB, Context: 1024K, License: openmdw-1.1, LLM Explorer Score: 0.29.

3-bit Base model:poolside/laguna-s-2... Base model:quantized:poolside/... Conversational Custom code Laguna Mlx Moe Oq Quantized Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/mlx-community/Laguna-S-2.1-oQ3e

Laguna S 2.1 OQ3e Parameters and Internals

LLM Name	Laguna S 2.1 OQ3e
Repository 🤗	https://huggingface.co/mlx-community/Laguna-S-2.1-oQ3e
Base Model(s)	poolside/Laguna-S-2.1 poolside/Laguna-S-2.1
Model Size	13.3b
Required VRAM	49 GB
Updated	2026-07-23
Maintainer	mlx-community
Model Type	laguna
Model Files	5.1 GB: 1-of-10 5.2 GB: 2-of-10 5.2 GB: 3-of-10 5.2 GB: 4-of-10 5.2 GB: 5-of-10 5.2 GB: 6-of-10 5.2 GB: 7-of-10 5.2 GB: 8-of-10 5.2 GB: 9-of-10 2.3 GB: 10-of-10
Model Architecture	LagunaForCausalLM
License	openmdw-1.1
Context Length	1048576
Model Max Length	1048576
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	〈\|PAD\|〉
Vocabulary Size	100352
Torch Data Type	bfloat16

Rank the Laguna S 2.1 OQ3e 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