What are the hardware requirements for Laguna Xs2 Dense K8 Cuda Sft?

Laguna Xs2 Dense K8 Cuda Sft requires approximately 6 GB of VRAM and supports a context window of 256K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Laguna Xs2 Dense K8 Cuda Sft and how large is it?

Laguna Xs2 Dense K8 Cuda Sft is developed by EvanOLeary, a model with 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 Xs2 Dense K8 Cuda Sft?

Laguna Xs2 Dense K8 Cuda Sft is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Laguna Xs2 Dense K8 Cuda Sft by EvanOLeary — VRAM 6GB, 256K context

Name: Laguna Xs2 Dense K8 Cuda Sft
Author: EvanOLeary

Laguna Xs2 Dense K8 Cuda Sft is an open-source language model by EvanOLeary. Features: 3b LLM, VRAM: 6GB, Context: 256K, License: apache-2.0, MoE, LLM Explorer Score: 0.24.

Base model:finetune:poolside/l... Base model:poolside/laguna-xs.... Code Conversational Cuda Custom code Densification En Endpoints compatible Kernels Laguna Laguna dense Moe Moe-to-dense Region:us Safetensors Sft

Model Card on HF 🤗: https://huggingface.co/EvanOLeary/laguna-xs2-dense-k8-cuda-sft

Laguna Xs2 Dense K8 Cuda Sft Parameters and Internals

LLM Name	Laguna Xs2 Dense K8 Cuda Sft
Repository 🤗	https://huggingface.co/EvanOLeary/laguna-xs2-dense-k8-cuda-sft
Base Model(s)	poolside/Laguna-XS.2 poolside/Laguna-XS.2
Model Size	3b
Required VRAM	6 GB
Updated	2026-07-27
Maintainer	EvanOLeary
Model Type	laguna_dense
Model Files	6.0 GB
Supported Languages	en
Model Architecture	LagunaForCausalLM
License	apache-2.0
Context Length	262144
Model Max Length	262144
Transformers Version	5.9.0
Tokenizer Class	TokenizersBackend
Padding Token	〈\|PAD\|〉
Vocabulary Size	100352

Rank the Laguna Xs2 Dense K8 Cuda Sft 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 Xs2 Dense K8 Cuda Sft

Best Alternatives	Context / RAM	Downloads	Likes
...aguna Xs2 Dense K8 Cuda Sft V2	256K / 6 GB	29	0