What are the hardware requirements for Laguna S 2.1 OQ2e Fast?

Laguna S 2.1 OQ2e Fast requires approximately 34.7 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 OQ2e Fast and how large is it?

Laguna S 2.1 OQ2e Fast is developed by mlx-community, a model with 9.6b 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 OQ2e Fast?

Laguna S 2.1 OQ2e Fast 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 OQ2e Fast by mlx-community — VRAM 34.7GB, 1024K context

Name: Laguna S 2.1 OQ2e Fast
Author: mlx-community

Laguna S 2.1 OQ2e Fast is an open-source language model by mlx-community. Features: 9.6b LLM, VRAM: 34.7GB, Context: 1024K, License: openmdw-1.1, LLM Explorer Score: 0.29.

2-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-oQ2e-fast

Laguna S 2.1 OQ2e Fast Parameters and Internals

LLM Name	Laguna S 2.1 OQ2e Fast
Repository 🤗	https://huggingface.co/mlx-community/Laguna-S-2.1-oQ2e-fast
Base Model(s)	poolside/Laguna-S-2.1 poolside/Laguna-S-2.1
Model Size	9.6b
Required VRAM	34.7 GB
Updated	2026-07-23
Maintainer	mlx-community
Model Type	laguna
Model Files	5.1 GB: 1-of-7 5.2 GB: 2-of-7 5.2 GB: 3-of-7 5.2 GB: 4-of-7 5.2 GB: 5-of-7 5.2 GB: 6-of-7 3.6 GB: 7-of-7
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 OQ2e Fast 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