What are the hardware requirements for Laguna S 2.1 AWQ INT4?

Laguna S 2.1 AWQ INT4 requires approximately 78.2 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 AWQ INT4 and how large is it?

Laguna S 2.1 AWQ INT4 is developed by cyankiwi, a model with 117.6b 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 AWQ INT4?

Laguna S 2.1 AWQ INT4 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 AWQ INT4 by cyankiwi — VRAM 78.2GB, 1024K context

Name: Laguna S 2.1 AWQ INT4
Author: cyankiwi

Laguna S 2.1 AWQ INT4 is an open-source language model by cyankiwi. Features: 117.6b LLM, VRAM: 78.2GB, Context: 1024K, License: openmdw-1.1, Quantized, LLM Explorer Score: 0.3.

Awq Base model:poolside/laguna-s-2... Base model:quantized:poolside/... Compressed-tensors Conversational Custom code Laguna Laguna-s-2.1 Quantized Region:us Safetensors Sharded Tensorflow Vllm

Model Card on HF 🤗: https://huggingface.co/cyankiwi/Laguna-S-2.1-AWQ-INT4

Laguna S 2.1 AWQ INT4 Parameters and Internals

LLM Name	Laguna S 2.1 AWQ INT4
Repository 🤗	https://huggingface.co/cyankiwi/Laguna-S-2.1-AWQ-INT4
Base Model(s)	poolside/Laguna-S-2.1 poolside/Laguna-S-2.1
Model Size	117.6b
Required VRAM	78.2 GB
Updated	2026-08-02
Maintainer	cyankiwi
Model Type	laguna
Model Files	5.4 GB: 1-of-15 5.4 GB: 2-of-15 5.4 GB: 3-of-15 5.4 GB: 4-of-15 5.4 GB: 5-of-15 5.4 GB: 6-of-15 5.4 GB: 7-of-15 5.4 GB: 8-of-15 5.4 GB: 9-of-15 5.4 GB: 10-of-15 5.4 GB: 11-of-15 5.4 GB: 12-of-15 5.4 GB: 13-of-15 5.4 GB: 14-of-15 2.6 GB: 15-of-15
AWQ Quantization	Yes
Quantization Type	awq
Model Architecture	LagunaForCausalLM
License	openmdw-1.1
Context Length	1048576
Model Max Length	1048576
Transformers Version	5.14.1
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	〈\|PAD\|〉
Vocabulary Size	100352

Rank the Laguna S 2.1 AWQ INT4 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 S 2.1 AWQ INT4

Best Alternatives	Context / RAM	Downloads	Likes
Laguna S 2.1 OptiQ 2bit	1024K / 44.2 GB	380	2
Laguna S 2.1 MLX 4bit	1024K / 65.8 GB	493	3
Laguna S 2.1 MLX 6bit	1024K / 95.4 GB	457	2
Laguna S 2.1	1024K / 214.2 GB	56445	708
Laguna S 2.1 INT4	1024K / 100.2 GB	191066	26
Laguna S 2.1 FP8	1024K / 116.8 GB	53942	26
Laguna S 2.1	1024K / 214.2 GB	569	7
Laguna S 2.1 Heretic	1024K / 219.3 GB	45	0

Note: green Score (e.g. "73.2") means that the model is better than cyankiwi/Laguna-S-2.1-AWQ-INT4.