OU

calderaai_13b-ouroboros

OuroborosGGUF by TheBlokeUpdated 2023-09-27
Download on Hugging Face
Parameters13B
Context2K
Layers40
Architecturellama
Smallest quant5.4 GB
Quick answer

calderaai_13b-ouroboros 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).

13B-Ouroboros, a 13B llama-based model in GGUF format

The CalderaAI 13B-Ouroboros model is a 13B parameter llama architecture trained on 2048 context tokens. It is available in multiple GGUF quantisations from Q2_K to Q8_0. The model is derived from a custom merge of several open‑source models.

Good at

  • Alpaca instruction prompting
  • Low perplexity on PTB dataset
  • Custom merge technique

Limits

  • No vision support
  • License is other
  • Context limited to 2048 tokens

Best for

  • Chat assistants
  • Instruction following
  • Text generation

Who it’s for. Developers and researchers who need a 13B llama model with multiple quantisation options for local inference. The model is suitable for CPU+GPU setups that support GGUF.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.4 GB 7.6 GB
Tight Get file →
Q3_K_S5.7 GB 7.8 GB
Tight Get file →
Q3_K_M6.3 GB 8.5 GB
Too big Get file →
Q3_K_L6.9 GB 9.1 GB
Too big Get file →
Q4_07.4 GB 9.5 GB
Too big Get file →
Q4_K_S7.4 GB 9.6 GB
Too big Get file →
Q4_K_M7.9 GB 10.0 GB
Too big Get file →
Q5_09.0 GB 11.2 GB
Too big Get file →
Q5_K_S9.0 GB 11.2 GB
Too big Get file →
Q5_K_M9.2 GB 11.4 GB
Too big Get file →
Q6_K10.7 GB 12.9 GB
Too big Get file →
Q8_013.8 GB 16.0 GB
Too big Get file →

For 8 GB VRAM, Q4_K_M (7.87 GB) or Q5_K_S (8.97 GB) are suitable. For 12 GB VRAM, Q4_K_M or Q5_K_M (9.23 GB) work well. For 16 GB VRAM, Q6_K (10.68 GB) or Q8_0 (13.83 GB) provide higher quality.

What GPU do you need for calderaai_13b-ouroboros?

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 calderaai_13b-ouroboros quant should you choose?

Q4_K_M is the usual starting point for calderaai_13b-ouroboros: 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 context2,048 tokens
KV cache (fp16)800 KB per token

Source

Quantized byTheBloke
FamilyOuroboros
Licenseother
Downloads (HF)1,438
Last updated2023-09-27

Frequently asked questions about calderaai_13b-ouroboros

How much VRAM does calderaai_13b-ouroboros 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 calderaai_13b-ouroboros 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 calderaai_13b-ouroboros 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 calderaai_13b-ouroboros support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 6.7 GB at 8K and 1.7 GB at 2K.

Where can I download calderaai_13b-ouroboros GGUF?

The files are on Hugging Face in the TheBloke/13B-Ouroboros-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 calderaai_13b-ouroboros use?

Hugging Face lists the license as other. 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 this model on 8 GB VRAM?

Yes, the Q4_K_M (7.87 GB) or Q5_K_S (8.97 GB) quantisations fit within 8 GB VRAM, with estimated memory usage around 15 GB at 8k context.

Does this model support vision tasks?

No, the model has no vision capabilities and is text‑only.

What context length does it support?

The model supports a maximum context length of 2048 tokens.

Other GGUFs of 13B-Ouroboros

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Ouroboros models

All Ouroboros →

Other medium models

All medium models →