LE

Leia Swallow 13b

LeiaGGUF by RichardErkhovUpdated 2024-08-14
Download on Hugging Face
Parameters13.1B
Context4K
Layers40
Architecturellama
Smallest quant4.9 GB
Quick answer

Leia Swallow 13b needs about 15.2 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 22 quants, from 4.9 GB (Q2_K) to 14.0 GB (Q8_0).

13.1B parameter Japanese‑English bilingual LLM based on LLaMA 2

Leia Swallow 13b is a 13.1B parameter model trained with LEIA to improve cross‑lingual transfer. It supports a 4096 token context and is licensed under apache‑2.0. The model excels in Japanese question answering and bilingual text generation.

Good at

  • Cross‑lingual Japanese‑English tasks
  • Japanese question answering
  • Bilingual text generation

Limits

  • 4096 token context
  • No vision support
  • Requires GGUF quantization

Best for

  • Japanese QA systems
  • Bilingual translation tools
  • Cross‑lingual research projects

Who it’s for. Developers and researchers needing a bilingual Japanese‑English LLM. The model is suitable for applications that require robust cross‑lingual performance and can run on systems supporting GGUF quantized models.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.9 GB 8.8 GB
Too big Get file →
IQ3_XS5.4 GB 9.3 GB
Too big Get file →
IQ3_S5.7 GB 9.6 GB
Too big Get file →
Q3_K_S5.7 GB 9.6 GB
Too big Get file →
IQ3_M6.1 GB 9.9 GB
Too big Get file →
Q3_K6.4 GB 10.3 GB
Too big Get file →
Q3_K_M6.4 GB 10.3 GB
Too big Get file →
Q3_K_L7.0 GB 10.9 GB
Too big Get file →
IQ4_XS7.1 GB 11.0 GB
Too big Get file →
Q4_07.4 GB 11.3 GB
Too big Get file →
IQ4_NL7.5 GB 11.3 GB
Too big Get file →
Q4_K_S7.5 GB 11.4 GB
Too big Get file →
Q4_K7.9 GB 11.8 GB
Too big Get file →
Q4_K_M7.9 GB 11.8 GB
Too big Get file →
Q4_18.3 GB 12.1 GB
Too big Get file →
Q5_09.1 GB 12.9 GB
Too big Get file →
Q5_K_S9.1 GB 12.9 GB
Too big Get file →
Q5_K9.3 GB 13.2 GB
Too big Get file →
Q5_K_M9.3 GB 13.2 GB
Too big Get file →
Q5_19.9 GB 13.7 GB
Too big Get file →
Q6_K10.8 GB 14.6 GB
Too big Get file →
Q8_014.0 GB 17.8 GB
Too big Get file →

For 12 GB VRAM, Q2_K (4.92 GB file, 12.1 GB memory at 8k context) is the smallest quant that fits. For 16 GB VRAM, Q3_K (6.41 GB file, 13.6 GB memory) or Q4_0 (7.45 GB file, 14.7 GB memory) are suitable. Larger VRAM allows higher‑quality quants such as Q5_K or Q6_K.

What GPU do you need for Leia Swallow 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_1 (8.3 GB file, about 15.5 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (14.0 GB file, about 21.2 GB in use).

Which Leia Swallow 13b quant should you choose?

Q4_K_M is the usual starting point for Leia Swallow 13b: it balances file size and quality well. Here it is a 7.9 GB file.

The Q8_0 file is 14.0 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 4.9 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
Parameters13.1B
Layers40
Trained context4,096 tokens
KV cache (fp16)800 KB per token

Source

Quantized byRichardErkhov
FamilyLeia
Licenseapache-2.0
Downloads (HF)740
Last updated2024-08-14

Frequently asked questions about Leia Swallow 13b

How much VRAM does Leia Swallow 13b need?

About 15.2 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 Leia Swallow 13b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Leia Swallow 13b GGUF?

It depends on the quant: Q2_K is 4.9 GB, IQ3_XS is 5.4 GB, IQ3_S is 5.7 GB, Q3_K_S is 5.7 GB, IQ3_M is 6.1 GB, Q3_K is 6.4 GB and 16 more.

What context length does Leia Swallow 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 Leia Swallow 13b GGUF?

The files are on Hugging Face in the RichardErkhov/leia-llm_-_Leia-Swallow-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 Leia Swallow 13b use?

Hugging Face lists the license as apache-2.0. 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 Leia Swallow 13b on 8 GB VRAM?

No, the smallest quant requires 12.1 GB memory at 8k context.

What context length does the model support?

The model supports a 4096 token context.

Is the model licensed for commercial use?

Yes, it is licensed under apache‑2.0.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Leia models

All Leia →

Other medium models

All medium models →