Swallow 70B needs about 44.7 GB of memory at Q4_K_M (a 41.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 10 quants, from 29.4 GB (Q2_K) to 48.9 GB (Q5_K_M).
Swallow 70B – 69.2B parameter LLaMA‑2 based model with Japanese and English support
Swallow 70B is a 69.2B parameter LLaMA‑2 derived model trained with extensive Japanese data. It offers instruction‑tuned variants and is available in GGUF format for local inference. The model supports a 4096 token context window.
Good at
- Japanese language tasks
- English language tasks
- Instruction following
Limits
- No vision support
- Requires large VRAM for full precision
- License is llama2
Best for
- Japanese text generation
- English text generation
- Instruction‑driven chat
Who it’s for. Developers and researchers needing a large Japanese‑capable LLM for local deployment. The model is suitable for applications that can accommodate the memory requirements of a 70B parameter model.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 29.4 GB | 31.2 GB | Too big | Get file → | |
| Q3_K_S | 30.0 GB | 31.9 GB | Too big | Get file → | |
| Q3_K_M | 33.3 GB | 35.1 GB | Too big | Get file → | |
| Q3_K_L | 36.3 GB | 38.1 GB | Too big | Get file → | |
| Q4_0 | 39.0 GB | 40.8 GB | Too big | Get file → | |
| Q4_K_S | 39.2 GB | 41.0 GB | Too big | Get file → | |
| Q4_K_M | 41.5 GB | 43.4 GB | Too big | Get file → | |
| Q5_0 | 47.6 GB | 49.4 GB | Too big | Get file → | |
| Q5_K_S | 47.6 GB | 49.4 GB | Too big | Get file → | |
| Q5_K_M | 48.9 GB | 50.7 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_0 (file size 39 GB, estimated 42.2 GB memory at 8 k context). For 12 GB VRAM, Q4_K_M (41.55 GB, 44.7 GB memory) is a good balance. For 16 GB VRAM, Q5_K_M (48.89 GB, 52.1 GB memory) provides higher quality.
What GPU do you need for Swallow 70B?
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: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: the best quant that fits is Q4_K_M (41.5 GB file, about 44.7 GB in use).
Which Swallow 70B quant should you choose?
Q4_K_M is the usual starting point for Swallow 70B: it balances file size and quality well. Here it is a 41.5 GB file.
If memory is tight, the smallest file is Q2_K at 29.4 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
Source
Frequently asked questions about Swallow 70B
How much VRAM does Swallow 70B need?
About 44.7 GB at Q4_K_M with an 8K context window. That is the 41.5 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 70B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 32.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Swallow 70B GGUF?
It depends on the quant: Q2_K is 29.4 GB, Q3_K_S is 30.0 GB, Q3_K_M is 33.3 GB, Q3_K_L is 36.3 GB, Q4_0 is 39.0 GB, Q4_K_S is 39.2 GB and 4 more.
What context length does Swallow 70B support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.7 GB at 8K and 1.3 GB at 4K.
Where can I download Swallow 70B GGUF?
The files are on Hugging Face in the TheBloke/Swallow-70B-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 70B 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 70B on 8 GB VRAM?
Only with a low‑precision quant like Q4_0, which still requires about 42.2 GB of VRAM at 8 k context, so 8 GB is insufficient.
Does Swallow 70B support vision tasks?
No, the model has no vision capability.
What license applies to Swallow 70B?
The model is licensed under llama2.