ST

StableBeluga 13B

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

StableBeluga 13B 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).

StableBeluga 13B – a 13B Llama2 fine‑tuned for English text

StableBeluga 13B is a 13B parameter Llama2 model fine‑tuned on an Orca‑style dataset. It is available in GGUF format and can be run with llama.cpp or compatible libraries. The model is licensed under the STABLE BELUGA NON‑COMMERCIAL COMMUNITY LICENSE AGREEMENT.

Good at

  • English language generation
  • Fine‑tuned conversational responses
  • Orca‑style instruction following

Limits

  • No vision support
  • Context limited to 4096 tokens
  • Requires GPU for efficient inference

Best for

  • Chatbot prototypes
  • Instruction‑based text generation
  • Research on fine‑tuned Llama2 models

Who it’s for. Developers and researchers who need a 13B Llama2 model fine‑tuned for English conversational tasks. The model is suitable for local inference using llama.cpp or other GGUF‑compatible tools.

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, estimated memory 14.6 GB). For 12 GB VRAM, Q5_0 or Q5_K_S (file size 8.97 GB, estimated memory 16.2 GB) provides a good balance. Larger VRAM allows Q6_K or Q8_0 for higher precision.

What GPU do you need for StableBeluga 13B?

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 StableBeluga 13B quant should you choose?

Q4_K_M is the usual starting point for StableBeluga 13B: 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
Licensellama2
Downloads (HF)728
Last updated2023-09-27

Frequently asked questions about StableBeluga 13B

How much VRAM does StableBeluga 13B 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 StableBeluga 13B 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 StableBeluga 13B 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 StableBeluga 13B 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 StableBeluga 13B GGUF?

The files are on Hugging Face in the TheBloke/StableBeluga-13B-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 StableBeluga 13B 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 StableBeluga 13B on 8 GB VRAM?

Yes, using Q4_0 or Q4_K_S quantizations, which require approximately 14.6 GB of VRAM at 8k context.

Does StableBeluga 13B support image inputs?

No, the model has no vision capabilities.

What license applies to the GGUF files?

The GGUF files are licensed under the STABLE BELUGA NON‑COMMERCIAL COMMUNITY LICENSE AGREEMENT.

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Stablebeluga models

All Stablebeluga →

Other medium models

All medium models →