What are the hardware requirements for 13B Thorns L2 AWQ?

13B Thorns L2 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 13B Thorns L2 AWQ and how large is it?

13B Thorns L2 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 13B Thorns L2 AWQ?

13B Thorns L2 AWQ is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

13B Thorns L2 AWQ by TheBloke — VRAM 7.2GB, 4K context

Name: 13B Thorns L2 AWQ
Author: TheBloke

13B Thorns L2 AWQ is an open-source language model by TheBloke. Features: 13b LLM, VRAM: 7.2GB, Context: 4K, License: llama2, Quantized, LLM Explorer Score: 0.09.

4-bit Alpaca Awq Base model:calderaai/13b-thorn... Base model:quantized:calderaai... Cot Llama Merge Mix Quantized Region:us Safetensors Uncensored Vicuna

Model Card on HF 🤗: https://huggingface.co/TheBloke/13B-Thorns-L2-AWQ

13B Thorns L2 AWQ Parameters and Internals

Model Type

LLaMA

Use Cases

Areas:

Research, Entertainment

Applications:

Roleplay, Conversation tasks

Limitations:

Uncensored and potentially generates misleading content.

Considerations:

Not suitable for use as factual advice.

Additional Notes

13B-Thorns-l2 utilizes a new merge method called Spherical Linear Interpolation. It is designed for merging LLaMA models and enhancing their performance by combining multiple models and LoRAs.

Training Details

Methodology:

Spherical Linear Interpolation (SLERP) for model merging

Safety Evaluation

Ethical Considerations:

WARNING - This Model Is Uncensored And Has Not Been Fully Tested For Toxicity.

Responsible Ai Considerations

Mitigation Strategies:

May generate offensive and misleading content.

Input Output

Input Format:

Alpaca format prompt template

Accepted Modalities:

text

Output Format:

text

LLM Name	13B Thorns L2 AWQ
Repository 🤗	https://huggingface.co/TheBloke/13B-Thorns-L2-AWQ
Model Name	13B Thorns L2
Model Creator	CalderaAI
Base Model(s)	13B Thorns L2 CalderaAI/13B-Thorns-l2
Model Size	13b
Required VRAM	7.2 GB
Updated	2026-08-08
Maintainer	TheBloke
Model Type	llama
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	4.31.0
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32032
Torch Data Type	float16

Rank the 13B Thorns L2 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 13B Thorns L2 AWQ

Best Alternatives	Context / RAM	Downloads	Likes
Yarn Llama 2 13B 128K AWQ	128K / 7.2 GB	4	2
LongAlign 13B 64K AWQ	64K / 7.2 GB	4	2
...oboros L2 13B 2 1 YaRN 64K AWQ	64K / 7.2 GB	5	2
OrcaMaid V3 13B 32K AWQ	32K / 7.2 GB	5	4
OrcaMaid V2 FIX 13B 32K AWQ	32K / 7.2 GB	7	1
NexusRaven V2 13B AWQ	16K / 7.2 GB	11	3
NexusRaven V2 13B AWQ	16K / 7.2 GB	1	3
...th CodeLlama 13B Python Hf AWQ	16K / 7.5 GB	6	0
WhiteRabbitNeo 13B AWQ	16K / 7.2 GB	332	4
NexusRaven V2 13B AWQ	16K / 7.2 GB	10	1

Note: green Score (e.g. "73.2") means that the model is better than TheBloke/13B-Thorns-L2-AWQ.