What are the hardware requirements for LoKuS 13B AWQ?

LoKuS 13B AWQ requires approximately 7.2 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed LoKuS 13B AWQ and how large is it?

LoKuS 13B AWQ is developed by TheBloke, a model with 13b 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 LoKuS 13B AWQ?

LoKuS 13B AWQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

LoKuS 13B AWQ by TheBloke — VRAM 7.2GB, 4K context

Name: LoKuS 13B AWQ
Author: TheBloke

LoKuS 13B AWQ is an open-source language model by TheBloke. Features: 13b LLM, VRAM: 7.2GB, Context: 4K, License: llama2, Quantized, Instruction-Based, LLM Explorer Score: 0.09.

4-bit Awq Base model:josw-14/lokus-13b Base model:quantized:josw-14/l... Instruct Llama Quantized Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/TheBloke/LoKuS-13B-AWQ

LoKuS 13B AWQ Parameters and Internals

Model Type

llama

Additional Notes

Quantized by TheBloke using AWQ, a low-bit weight quantization method. Supports 4-bit quantization.

Input Output

Input Format:

Below is an instruction that describes a task. Write a response that appropriately completes the request. ### Instruction: {prompt} ### Response:

LLM Name	LoKuS 13B AWQ
Repository 🤗	https://huggingface.co/TheBloke/LoKuS-13B-AWQ
Model Name	LoKuS 13B
Model Creator	Jonathan Swarp
Base Model(s)	LoKuS 13B JoSw-14/LoKuS-13B
Model Size	13b
Required VRAM	7.2 GB
Updated	2026-08-05
Maintainer	TheBloke
Model Type	llama
Instruction-Based	Yes
Model Files	7.2 GB
AWQ Quantization	Yes
Quantization Type	awq
Model Architecture	LlamaForCausalLM
License	llama2
Context Length	4096
Model Max Length	4096
Transformers Version	4.32.1
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32001
Torch Data Type	float16

Rank the LoKuS 13B AWQ 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 LoKuS 13B AWQ

Best Alternatives	Context / RAM	Downloads	Likes
CodeLlama 13B Instruct AWQ	16K / 7.2 GB	261	9
NexusRaven 13B AWQ	16K / 7.2 GB	22	4
...ma 13B Instruct Hf W4 G128 AWQ	16K / 7.2 GB	10	0
Meta Llama 3 13B Instruct AWQ	8K / 8.8 GB	8	0
Leo Hessianai 13B Chat AWQ	8K / 7.2 GB	6	1
...ssianai 13B Chat Bilingual AWQ	8K / 7.2 GB	4	1
Swallow 13B Instruct AWQ	4K / 7.5 GB	10	1
Mythalion 13B AWQ	4K / 7.2 GB	255	10
Pygmalion 2 13B AWQ	4K / 7.2 GB	11	6
Speechless Llama2 13B AWQ	4K / 7.2 GB	7	1

Note: green Score (e.g. "73.2") means that the model is better than TheBloke/LoKuS-13B-AWQ.