SmaugDolphin-60B needs about 28.8 GB of memory at Q3_K_S (a 26.3 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 5 quants, from 22.4 GB (Q2_K) to 27.1 GB (IQ3_M). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.
SmaugDolphin-60B is a 60.8B-parameter Smaugdolphin model in GGUF format, quantized by RichardErkhov. Its trained context length is 195K tokens. The repository has 5 quant files, from 22.4 GB (Q2_K) to 27.1 GB (IQ3_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 22.4 GB | 24.9 GB | Too big | Get file → | |
| IQ3_XS | 25.0 GB | 27.5 GB | Too big | Get file → | |
| Q3_K_S | 26.3 GB | 28.8 GB | Too big | Get file → | |
| IQ3_S | 26.4 GB | 28.9 GB | Too big | Get file → | |
| IQ3_M | 27.1 GB | 29.6 GB | Too big | Get file → |
What GPU do you need for SmaugDolphin-60B?
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 IQ3_M (27.1 GB file, about 29.6 GB in use).
Which SmaugDolphin-60B quant should you choose?
Q3_K_S (26.3 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
If memory is tight, the smallest file is Q2_K at 22.4 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
Frequently asked questions about SmaugDolphin-60B
How much VRAM does SmaugDolphin-60B need?
About 28.8 GB at Q3_K_S with an 8K context window. That is the 26.3 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 SmaugDolphin-60B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 24.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of SmaugDolphin-60B GGUF?
It depends on the quant: Q2_K is 22.4 GB, IQ3_XS is 25.0 GB, Q3_K_S is 26.3 GB, IQ3_S is 26.4 GB, IQ3_M is 27.1 GB.
What context length does SmaugDolphin-60B support?
The GGUF header lists a trained context length of 200,000 tokens (195K). The KV cache grows with the context you use: about 2.0 GB at 8K and 8.1 GB at 32K.
Where can I download SmaugDolphin-60B GGUF?
The files are on Hugging Face in the RichardErkhov/macadeliccc_-_SmaugDolphin-60B-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.