What are the hardware requirements for Spring Dragon?

Spring Dragon requires approximately 26 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 Spring Dragon and how large is it?

Spring Dragon is developed by Henk717, 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 Spring Dragon?

Spring Dragon is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Spring Dragon by Henk717 — VRAM 26GB, 4K context

Name: Spring Dragon
Author: Henk717

Spring Dragon is an open-source language model by Henk717. Features: 13b LLM, VRAM: 26GB, Context: 4K, License: llama2, LLM Explorer Score: 0.09.

Endpoints compatible Llama Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/Henk717/spring-dragon

Spring Dragon Benchmarks

LLME Score: 0.08577

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

🌟 Advertise your project 🚀

Spring Dragon Parameters and Internals

Model Type

text adventure

Use Cases

Primary Use Cases:

text adventure gaming

Limitations:

Not recommended for use in model merges

Considerations:

Primarily intended for nostalgic users looking for a 2020 era text adventure experience

Additional Notes

Model recreated from the text_adventures.txt file to invoke similar experience to the AI Dungeon 2 Dragon model but labeled 'Spring Dragon' due to developmental expectations.

Input Output

Input Format:

Second person prompts

Accepted Modalities:

text

Output Format:

Text

Performance Tips:

Prefix actions with "You" for best performance

LLM Name	Spring Dragon
Repository 🤗	https://huggingface.co/Henk717/spring-dragon
Model Size	13b
Required VRAM	26 GB
Updated	2026-05-16
Maintainer	Henk717
Model Type	llama
Model Files	9.9 GB: 1-of-3 9.9 GB: 2-of-3 6.2 GB: 3-of-3
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	32000
Torch Data Type	float16

Quantized Models of the Spring Dragon

Model	Likes	Downloads	VRAM
Spring Dragon GGUF	6	396	5 GB
Spring Dragon AWQ	0	9	7 GB
Spring Dragon GPTQ	9	24	7 GB
Spring Dragon GGML	3	3	5 GB

Best Alternatives to Spring Dragon

Best Alternatives	Context / RAM	Downloads	Likes
Yarn Llama 2 13B 128K	128K / 26 GB	1657	113
Luminaura RP 13B	128K / 26 GB	15	1
Agent Llama2 13B 80K	80K / 26.4 GB	5	0
Chat Llama2 13B 80K	80K / 52.8 GB	11	0
LongAlign 13B 64K	64K / 26 GB	53	13
LongAlign 13B 64K	64K / 26 GB	11	13
LongAlign 13B 64K Base	64K / 26 GB	41	3
LongAlign 13B 64K Base	64K / 26 GB	6	3
Openbuddy Llama2 13B V15p1 64K	64K / 26.1 GB	7	4
Yarn Llama 2 13B 64K	64K / 26 GB	1865	18

Note: green Score (e.g. "73.2") means that the model is better than Henk717/spring-dragon.

Rank the Spring Dragon Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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

What open-source LLMs or SLMs are you in search of? 53972 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

Spring Dragon by Henk717