SW

Swallow 13B Instruct

SwallowGGUF by TheBlokeUpdated 2023-12-19
Download on Hugging Face
Parameters13.1B
Context4K
Layers40
Architecturellama
Smallest quant5.5 GB
Quick answer

Swallow 13B Instruct 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 12 quants, from 5.5 GB (Q2_K) to 14.0 GB (Q8_0).

Swallow 13B Instruct – Japanese‑English instruction‑tuned LLaMA‑2 model

Swallow 13B Instruct is a 13.1B parameter LLaMA‑2 model fine‑tuned for instruction following in Japanese and English. It was released on April 26, 2024 as a preview version and supports a 4096 token context window.

Good at

  • Japanese language tasks
  • Instruction following
  • Bilingual English‑Japanese dialogue

Limits

  • 4096 token context
  • No vision support
  • License: llama2

Best for

  • Japanese‑English translation
  • Japanese QA and summarization
  • Bilingual chat applications

Who it’s for. Developers and researchers who need a bilingual Japanese‑English LLM for instruction‑driven tasks. The model is suitable for applications that require Japanese language understanding and English instruction compliance.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.5 GB 9.4 GB
Too big Get file →
Q3_K_S5.7 GB 9.6 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 →
Q4_07.4 GB 11.3 GB
Too big Get file →
Q4_K_S7.5 GB 11.3 GB
Too big Get file →
Q4_K_M7.9 GB 11.8 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_K_M9.3 GB 13.2 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 a 8 GB VRAM system, use the Q2_K quant (5.5 GB file, ~12.7 GB memory at 8 k context). If more VRAM is available, Q3_K_M (6.41 GB file, ~13.6 GB memory) or Q4_K_M (7.95 GB file, ~15.2 GB memory) provide better quality. Larger quants such as Q5_K_M or Q6_K require 16–18 GB memory and are suited for high‑end GPUs.

What GPU do you need for Swallow 13B Instruct?

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 15.2 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 Swallow 13B Instruct quant should you choose?

Q4_K_M is the usual starting point for Swallow 13B Instruct: 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 5.5 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 byTheBloke
FamilySwallow
Licensellama2
Downloads (HF)1,223
Last updated2023-12-19

Frequently asked questions about Swallow 13B Instruct

How much VRAM does Swallow 13B Instruct 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 Swallow 13B Instruct on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Swallow 13B Instruct GGUF?

It depends on the quant: Q2_K is 5.5 GB, Q3_K_S is 5.7 GB, Q3_K_M is 6.4 GB, Q3_K_L is 7.0 GB, Q4_0 is 7.4 GB, Q4_K_S is 7.5 GB and 6 more.

What context length does Swallow 13B Instruct 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 Swallow 13B Instruct GGUF?

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

The Q2_K quant needs ~12.7 GB memory at 8 k context, so 8 GB VRAM is insufficient. Use a lower‑quant model or a larger GPU.

What context length does the model support?

The model supports a 4096 token context window.

Is the model licensed for commercial use?

The model is licensed under llama2; commercial use terms are not specified in the provided data.

Other GGUFs of Swallow-13b-instruct-hf

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Swallow models

All Swallow →

Other medium models

All medium models →