Smaug 72B v0.1 iMat needs about 43.7 GB of memory at IQ2_XS (a 21.8 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 6 quants, from 16.2 GB (IQ1_S) to 28.7 GB (IQ3_XXS). Longer context needs more: at 32K tokens the KV cache alone adds about 85.9 GB.
Smaug 72B v0.1 iMat is a 72.3B-parameter Smaug model in GGUF format, quantized by dranger003. Its trained context length is 32K tokens. The repository has 6 quant files, from 16.2 GB (IQ1_S) to 28.7 GB (IQ3_XXS).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 16.2 GB | 38.2 GB | Too big | Get file → | |
| IQ2_XXS | 19.8 GB | 41.8 GB | Too big | Get file → | |
| IQ2_XS | 21.8 GB | 43.7 GB | Too big | Get file → | |
| IQ2_S | 23.4 GB | 45.4 GB | Too big | Get file → | |
| IQ2_M | 25.2 GB | 47.1 GB | Too big | Get file → | |
| IQ3_XXS | 28.7 GB | 50.7 GB | Too big | Get file → |
What GPU do you need for Smaug 72B v0.1 iMat?
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 IQ2_M (25.2 GB file, about 47.1 GB in use).
Which Smaug 72B v0.1 iMat quant should you choose?
IQ2_XS (21.8 GB) is the middle option in this repository. 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.
If memory is tight, the smallest file is IQ1_S at 16.2 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 Smaug 72B v0.1 iMat
How much VRAM does Smaug 72B v0.1 iMat need?
About 43.7 GB at IQ2_XS with an 8K context window. That is the 21.8 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 Smaug 72B v0.1 iMat on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 38.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Smaug 72B v0.1 iMat GGUF?
It depends on the quant: IQ1_S is 16.2 GB, IQ2_XXS is 19.8 GB, IQ2_XS is 21.8 GB, IQ2_S is 23.4 GB, IQ2_M is 25.2 GB, IQ3_XXS is 28.7 GB.
What context length does Smaug 72B v0.1 iMat support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 21.5 GB at 8K and 85.9 GB at 32K.
Where can I download Smaug 72B v0.1 iMat GGUF?
The files are on Hugging Face in the dranger003/Smaug-72B-v0.1-iMat.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 Smaug 72B v0.1 iMat 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.