SW

Swallow 7B Instruct

SwallowGGUF by TheBlokeUpdated 2023-12-19
Download on Hugging Face
Parameters6.83B
Context4K
Layers32
Architecturellama
Smallest quant2.9 GB
Quick answer

Swallow 7B Instruct needs about 8.9 GB of memory at Q4_K_M (a 4.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 12 quants, from 2.9 GB (Q2_K) to 7.3 GB (Q8_0).

Swallow 7B Instruct – 6.83B LLaMA‑2 based Japanese/English instruction model

Swallow 7B Instruct is a 6.83B parameter LLaMA‑2 derived model fine‑tuned for instruction following. It supports Japanese and English text and is available in multiple GGUF quantisations. The model was released by TokyoTech‑LLM and distributed by TheBloke.

Good at

  • Instruction following in Japanese and English
  • Efficient inference with quantised GGUF files
  • Large context handling up to 4096 tokens

Limits

  • No vision capabilities
  • Requires GPU for best performance
  • License is llama2, not open for commercial redistribution

Best for

  • Local instruction‑driven chatbots
  • Japanese language tutoring
  • Rapid prototyping of LLM applications

Who it’s for. Developers and researchers who need a Japanese‑capable instruction model that runs locally. The model is suitable for those who prefer open‑source LLMs and can provide a GPU for inference.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K2.9 GB 5.5 GB
Fits Get file →
Q3_K_S3.0 GB 5.7 GB
Fits Get file →
Q3_K_M3.4 GB 6.0 GB
Fits Get file →
Q3_K_L3.7 GB 6.3 GB
Fits Get file →
Q4_03.9 GB 6.5 GB
Fits Get file →
Q4_K_S3.9 GB 6.6 GB
Fits Get file →
Q4_K_M4.1 GB 6.8 GB
Fits Get file →
Q5_04.7 GB 7.4 GB
Tight Get file →
Q5_K_S4.7 GB 7.4 GB
Tight Get file →
Q5_K_M4.9 GB 7.5 GB
Tight Get file →
Q6_K5.6 GB 8.3 GB
Too big Get file →
Q8_07.3 GB 9.9 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (4.14 GB file, ~8.9 GB memory). For 12 GB VRAM, Q6_K (5.6 GB file, ~10.4 GB memory) or Q8_0 (7.26 GB file, ~12.1 GB memory). Smaller VRAM budgets can use Q4_0 or Q3_K_S. Estimates are approximate.

What GPU do you need for Swallow 7B 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: the best quant that fits is Q3_K_S (3.0 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (5.6 GB file, about 10.4 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (7.3 GB file, about 12.1 GB in use).

Which Swallow 7B Instruct quant should you choose?

Q4_K_M is the usual starting point for Swallow 7B Instruct: it balances file size and quality well. Here it is a 4.1 GB file.

The Q8_0 file is 7.3 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 2.9 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
Parameters6.83B
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized byTheBloke
FamilySwallow
Licensellama2
Downloads (HF)2,149
Last updated2023-12-19

Frequently asked questions about Swallow 7B Instruct

How much VRAM does Swallow 7B Instruct need?

About 8.9 GB at Q4_K_M with an 8K context window. That is the 4.1 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 7B Instruct on an 8 GB GPU?

Yes, with Q3_K_S: the 3.0 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Swallow 7B Instruct GGUF?

It depends on the quant: Q2_K is 2.9 GB, Q3_K_S is 3.0 GB, Q3_K_M is 3.4 GB, Q3_K_L is 3.7 GB, Q4_0 is 3.9 GB, Q4_K_S is 3.9 GB and 6 more.

What context length does Swallow 7B 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 4.3 GB at 8K and 2.1 GB at 4K.

Where can I download Swallow 7B Instruct GGUF?

The files are on Hugging Face in the TheBloke/Swallow-7B-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 7B 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 7B Instruct on 8 GB VRAM?

Yes, using Q4_K_M or Q4_0 quantisations will fit within 8 GB VRAM with approximate memory usage of 8.9 GB or 8.7 GB.

Does Swallow 7B Instruct support image input?

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

What license applies to Swallow 7B Instruct?

The model is licensed under the llama2 license, which restricts commercial redistribution.

Other GGUFs of Swallow-7b-instruct-hf

Similar models

Browse all →

More from TheBloke

All by TheBloke →

More Swallow models

All Swallow →

Other small models

All small models →