Swallow 7B 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 – a Japanese‑English LLaMA‑2 based model in GGUF format
Swallow 7B is a 6.83 billion parameter LLaMA‑2 derived model tuned with Japanese data. It is available in multiple quantisations for llama.cpp and compatible GUIs. The model supports a 4096‑token context window and is licensed under llama2.
Good at
- Japanese language tasks
- English language tasks
- Instruction‑tuned variants
Limits
- No vision support
- Requires GPU for efficient inference
- License restricts commercial use
Best for
- Local Japanese‑English chatbots
- Japanese text summarisation
- Japanese‑English translation
Who it’s for. Developers and researchers needing a lightweight Japanese‑English LLM for local deployment. The model is suitable for projects that require instruction‑tuned behaviour without large GPU resources.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 2.9 GB | 5.5 GB | Fits | Get file → | |
| Q3_K_S | 3.0 GB | 5.7 GB | Fits | Get file → | |
| Q3_K_M | 3.4 GB | 6.0 GB | Fits | Get file → | |
| Q3_K_L | 3.7 GB | 6.3 GB | Fits | Get file → | |
| Q4_0 | 3.9 GB | 6.5 GB | Fits | Get file → | |
| Q4_K_S | 3.9 GB | 6.6 GB | Fits | Get file → | |
| Q4_K_M | 4.1 GB | 6.8 GB | Fits | Get file → | |
| Q5_0 | 4.7 GB | 7.4 GB | Tight | Get file → | |
| Q5_K_S | 4.7 GB | 7.4 GB | Tight | Get file → | |
| Q5_K_M | 4.9 GB | 7.5 GB | Tight | Get file → | |
| Q6_K | 5.6 GB | 8.3 GB | Too big | Get file → | |
| Q8_0 | 7.3 GB | 9.9 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (est. 8.9 GB memory at 8k context). For 12 GB VRAM, Q8_0 (12.1 GB) offers full precision. Smaller VRAM budgets can use Q2_K or Q3_K_S, which need 7.7–7.8 GB memory at 8k context.
What GPU do you need for Swallow 7B?
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 quant should you choose?
Q4_K_M is the usual starting point for Swallow 7B: 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
Source
Frequently asked questions about Swallow 7B
How much VRAM does Swallow 7B 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 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 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 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 GGUF?
The files are on Hugging Face in the TheBloke/Swallow-7B-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 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 on 8 GB VRAM?
Yes, the Q4_K_M quantisation requires about 8.9 GB memory at 8k context, which fits within an 8 GB VRAM budget with some overhead.
Does Swallow 7B support image inputs?
No, the model does not have vision capabilities; it is purely text‑based.
What license applies to Swallow 7B?
The model is released under the llama2 license, which allows research and non‑commercial use.