Swallow-70b-instruct-v0.1 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 20 quants, from 14.6 GB (IQ1_S) to 48.9 GB (Q5_K_M).
Swallow‑70b‑instruct‑v0.1 – a 70.2B‑parameter instruction‑tuned LLaMA model
Swallow‑70b‑instruct‑v0.1 is a 70.2B‑parameter LLaMA‑2 based model fine‑tuned for instruction following. It supports Japanese and English and is available in multiple GGUF quantizations. The model was released on April 26, 2024 as part of the Swallow‑v0.1 preview.
Good at
- Instruction following in Japanese and English
- Large context handling up to 4096 tokens
- High‑parameter capacity for detailed responses
Limits
- Requires large VRAM; 8k context needs 17.8–52.1 GB depending on quant
- No vision or multimodal support
- License is llama2 – use per terms
Best for
- Chatbots needing detailed Japanese support
- Research prototyping with large‑parameter models
- Generating long, context‑rich content
Who it’s for. Developers and researchers who need a high‑parameter LLaMA model with instruction tuning and Japanese language support. The model is suitable for local deployment using llama.cpp with sufficient GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 14.6 GB | 16.5 GB | Too big | Get file → | |
| IQ1_M | 16.0 GB | 17.9 GB | Too big | Get file → | |
| IQ2_XXS | 18.4 GB | 20.2 GB | Too big | Get file → | |
| IQ2_XS | 20.4 GB | 22.3 GB | Too big | Get file → | |
| IQ2_S | 21.5 GB | 23.3 GB | Too big | Get file → | |
| IQ2_M | 23.3 GB | 25.2 GB | Too big | Get file → | |
| Q2_K | 25.6 GB | 27.4 GB | Too big | Get file → | |
| IQ3_XXS | 26.7 GB | 28.5 GB | Too big | Get file → | |
| IQ3_XS | 28.4 GB | 30.3 GB | Too big | Get file → | |
| IQ3_S | 30.0 GB | 31.9 GB | Too big | Get file → | |
| Q3_K_S | 30.0 GB | 31.9 GB | Too big | Get file → | |
| IQ3_M | 31.1 GB | 32.9 GB | Too big | Get file → | |
| Q3_K_M | 33.4 GB | 35.2 GB | Too big | Get file → | |
| Q3_K_L | 36.3 GB | 38.1 GB | Too big | Get file → | |
| IQ4_XS | 37.0 GB | 38.8 GB | Too big | Get file → | |
| Q4_0 | 39.1 GB | 41.0 GB | Too big | Get file → | |
| Q4_K_S | 39.4 GB | 41.2 GB | Too big | Get file → | |
| Q4_K_M | 41.5 GB | 43.4 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 IQ1_S (14.63 GB file, 17.8 GB memory). For 16 GB VRAM, IQ1_M (16.04 GB file, 19.2 GB memory). For 24 GB VRAM, Q2_K (25.57 GB file, 28.8 GB memory). Larger VRAM allows higher‑quality quants such as Q5_K_M.
What GPU do you need for Swallow-70b-instruct-v0.1?
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: the best quant that fits is IQ2_XS (20.4 GB file, about 23.6 GB in use).
- 32 GB VRAM: the best quant that fits is IQ3_XS (28.4 GB file, about 31.6 GB in use).
- 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-instruct-v0.1 quant should you choose?
Q4_K_M is the usual starting point for Swallow-70b-instruct-v0.1: it balances file size and quality well. Here it is a 41.5 GB file.
If memory is tight, the smallest file is IQ1_S at 14.6 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-instruct-v0.1
How much VRAM does Swallow-70b-instruct-v0.1 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-instruct-v0.1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 17.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Swallow-70b-instruct-v0.1 GGUF?
It depends on the quant: IQ1_S is 14.6 GB, IQ1_M is 16.0 GB, IQ2_XXS is 18.4 GB, IQ2_XS is 20.4 GB, IQ2_S is 21.5 GB, IQ2_M is 23.3 GB and 14 more.
What context length does Swallow-70b-instruct-v0.1 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-instruct-v0.1 GGUF?
The files are on Hugging Face in the mradermacher/Swallow-70b-instruct-v0.1-i1-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-instruct-v0.1 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‑instruct‑v0.1 on 8 GB VRAM?
No. The smallest quant requires 17.8 GB memory at 8k context. 8 GB VRAM is insufficient.
Does the model support vision or multimodal inputs?
No, the model is purely text‑based and does not support vision.
What license applies to this model?
The model is licensed under the llama2 license, which allows research and commercial use with attribution.