SP

Spring Dragon

SpringGGUF by TheBlokeUpdated 2023-09-27
Download on Hugging Face
Parameters13B
Context4K
Layers40
Architecturellama
Smallest quant5.4 GB
Quick answer

Spring Dragon needs about 15.1 GB of memory at Q4_K_M (a 7.9 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 12 quants, from 5.4 GB (Q2_K) to 13.8 GB (Q8_0).

Spring Dragon – a 13B llama model for nostalgic text adventures

Spring Dragon is a 13B llama model recreated from the 2020 AI Dungeon 2 Dragon model. It is designed for text adventure generation with a 4096 token context. The model is released under the llama2 license.

Good at

  • Text adventure storytelling
  • Second‑person narrative generation
  • Retro game lore recreation

Limits

  • No vision support
  • Designed for text only
  • Not recommended for merges

Best for

  • KoboldAI adventure mode
  • Story‑based chatbots
  • Retro game content creation

Who it’s for. Developers and hobbyists who want to run a 2020‑era text adventure model locally. It is suitable for users who prefer a lightweight, single‑purpose model over modern instruct models.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.4 GB 9.3 GB
Too big Get file →
Q3_K_S5.7 GB 9.5 GB
Too big Get file →
Q3_K_M6.3 GB 10.2 GB
Too big Get file →
Q3_K_L6.9 GB 10.8 GB
Too big Get file →
Q4_07.4 GB 11.2 GB
Too big Get file →
Q4_K_S7.4 GB 11.3 GB
Too big Get file →
Q4_K_M7.9 GB 11.7 GB
Too big Get file →
Q5_09.0 GB 12.8 GB
Too big Get file →
Q5_K_S9.0 GB 12.8 GB
Too big Get file →
Q5_K_M9.2 GB 13.1 GB
Too big Get file →
Q6_K10.7 GB 14.5 GB
Too big Get file →
Q8_013.8 GB 17.7 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 or Q4_K_S (file size 7.37 GB or 7.41 GB, estimated memory 14.6 GB). For 12 GB VRAM, Q5_0 or Q5_K_S (8.97 GB, 16.2 GB). For 16 GB VRAM, Q6_K (10.68 GB, 17.9 GB).

What GPU do you need for Spring Dragon?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is Q4_K_M (7.9 GB file, about 15.1 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (13.8 GB file, about 21.0 GB in use).

Which Spring Dragon quant should you choose?

Q4_K_M is the usual starting point for Spring Dragon: it balances file size and quality well. Here it is a 7.9 GB file.

The Q8_0 file is 13.8 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 5.4 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters13B
Layers40
Trained context4,096 tokens
KV cache (fp16)800 KB per token

Source

Quantized byTheBloke
FamilySpring
Licensellama2
Downloads (HF)1,058
Last updated2023-09-27

Frequently asked questions about Spring Dragon

How much VRAM does Spring Dragon need?

About 15.1 GB at Q4_K_M with an 8K context window. That is the 7.9 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Spring Dragon on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Spring Dragon GGUF?

It depends on the quant: Q2_K is 5.4 GB, Q3_K_S is 5.7 GB, Q3_K_M is 6.3 GB, Q3_K_L is 6.9 GB, Q4_0 is 7.4 GB, Q4_K_S is 7.4 GB and 6 more.

What context length does Spring Dragon support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 6.7 GB at 8K and 3.4 GB at 4K.

Where can I download Spring Dragon GGUF?

The files are on Hugging Face in the TheBloke/Spring-Dragon-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Spring Dragon use?

Hugging Face lists the license as llama2. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Spring Dragon on 8 GB VRAM?

The Q4_0 and Q4_K_S variants require about 14.6 GB of VRAM, so 8 GB is insufficient.

Does Spring Dragon support image input?

No, the model has no vision capabilities.

Is Spring Dragon suitable for merges?

It is not recommended for merges due to its specialized design.

Other GGUFs of spring-dragon

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Spring models

All Spring →

Other medium models

All medium models →