What are the hardware requirements for Laguna XS.2 Mxfp8?

Laguna XS.2 Mxfp8 requires approximately 34.3 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Laguna XS.2 Mxfp8 and how large is it?

Laguna XS.2 Mxfp8 is developed by mlx-community, a model with 33.4b 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 Laguna XS.2 Mxfp8?

Laguna XS.2 Mxfp8 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Laguna XS.2 Mxfp8 by mlx-community — VRAM 34.3GB, 128K context

Name: Laguna XS.2 Mxfp8
Author: mlx-community

Laguna XS.2 Mxfp8 is an open-source language model by mlx-community. Features: 33.4b LLM, VRAM: 34.3GB, Context: 128K, License: apache-2.0, LLM Explorer Score: 0.25.

8-bit Base model:poolside/laguna-xs.... Base model:quantized:poolside/... Conversational Custom code Laguna Laguna-xs.2 Mlx Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/mlx-community/Laguna-XS.2-mxfp8

Laguna XS.2 Mxfp8 Parameters and Internals

LLM Name	Laguna XS.2 Mxfp8
Repository 🤗	https://huggingface.co/mlx-community/Laguna-XS.2-mxfp8
Base Model(s)	poolside/Laguna-XS.2 poolside/Laguna-XS.2
Model Size	33.4b
Required VRAM	34.3 GB
Updated	2026-08-08
Maintainer	mlx-community
Model Type	laguna
Model Files	5.2 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 3.1 GB: 7-of-7
Model Architecture	LagunaForCausalLM
License	apache-2.0
Context Length	131072
Model Max Length	131072
Tokenizer Class	TokenizersBackend
Padding Token	〈\|PAD\|〉
Vocabulary Size	100352
Torch Data Type	bfloat16

Rank the Laguna XS.2 Mxfp8 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 Laguna XS.2 Mxfp8

Best Alternatives	Context / RAM	Downloads	Likes
Laguna XS 2.1	256K / 66.6 GB	29567	194
Laguna XS.2	256K / 66.6 GB	89693	316
Laguna XS 2.1 NVFP4	256K / 21.5 GB	20828	14
Laguna XS 2.1 FP8	256K / 35.2 GB	9664	8
Laguna XS 2.1 NVFP4 Mlx	256K / 21.6 GB	2057	3
Laguna XS 2.1 Bf16	256K / 67.3 GB	491	1
Laguna XS.2 FP8	256K / 35.2 GB	564	13
Laguna XS.2 Nvfp4	128K / 18.9 GB	100	1
Laguna XS 2.1 OptiQ 4bit	256K / 20.9 GB	67	2
Laguna XS.2 4bit	128K / 18.9 GB	356	4

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Laguna-XS.2-mxfp8.