Amaterasu 123B needs about 76.7 GB of memory at Q4_K_M (a 73.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 19 quants, from 26.0 GB (IQ1_S) to 245.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 11.8 GB.
Amaterasu 123B is a 123B-parameter Amaterasu model in GGUF format, quantized by Aratako. Its trained context length is 128K tokens. The repository has 19 quant files, from 26.0 GB (IQ1_S) to 245.2 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 26.0 GB | 29.4 GB | Too big | Get file → | |
| IQ1_M | 28.4 GB | 31.8 GB | Too big | Get file → | |
| IQ2_XXS | 32.4 GB | 35.9 GB | Too big | Get file → | |
| IQ2_XS | 36.1 GB | 39.5 GB | Too big | Get file → | |
| IQ2_S | 38.4 GB | 41.8 GB | Too big | Get file → | |
| IQ2_M | 41.6 GB | 45.1 GB | Too big | Get file → | |
| IQ3_XXS | 47.0 GB | 50.5 GB | Too big | Get file → | |
| IQ3_XS | 50.1 GB (2 parts) | 53.6 GB | Too big | Get file → | |
| IQ3_S | 53.0 GB (2 parts) | 56.4 GB | Too big | Get file → | |
| IQ3_M | 55.3 GB (2 parts) | 58.7 GB | Too big | Get file → | |
| IQ4_XS | 65.4 GB (2 parts) | 68.9 GB | Too big | Get file → | |
| IQ4_NL | 69.2 GB (2 parts) | 72.7 GB | Too big | Get file → | |
| Q4_K_M | 73.2 GB (2 parts) | 76.7 GB | Too big | Get file → | |
| Q4_K_S | 73.2 GB (2 parts) | 76.7 GB | Too big | Get file → | |
| Q5_K_S | 84.4 GB (2 parts) | 87.8 GB | Too big | Get file → | |
| Q5_K_M | 86.5 GB (2 parts) | 89.9 GB | Too big | Get file → | |
| Q6_K | 100.6 GB (3 parts) | 104.0 GB | Too big | Get file → | |
| Q8_0 | 130.3 GB (3 parts) | 133.7 GB | Too big | Get file → | |
| BF16 | 245.2 GB (5 parts) | 248.7 GB | Too big | Get file → |
What GPU do you need for Amaterasu 123B?
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: the best quant that fits is IQ1_M (28.4 GB file, about 31.8 GB in use).
- 48 GB VRAM: the best quant that fits is IQ2_M (41.6 GB file, about 45.1 GB in use).
Which Amaterasu 123B quant should you choose?
Q4_K_M is the usual starting point for Amaterasu 123B: it balances file size and quality well. Here it is a 73.2 GB file.
The Q8_0 file is 130.3 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 IQ1_S at 26.0 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 Amaterasu 123B
How much VRAM does Amaterasu 123B need?
About 76.7 GB at Q4_K_M with an 8K context window. That is the 73.2 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 Amaterasu 123B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 29.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Amaterasu 123B GGUF?
It depends on the quant: IQ1_S is 26.0 GB, IQ1_M is 28.4 GB, IQ2_XXS is 32.4 GB, IQ2_XS is 36.1 GB, IQ2_S is 38.4 GB, IQ2_M is 41.6 GB and 13 more.
What context length does Amaterasu 123B support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.0 GB at 8K and 11.8 GB at 32K.
Where can I download Amaterasu 123B GGUF?
The files are on Hugging Face in the Aratako/Amaterasu-123B-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 Amaterasu 123B use?
Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.