Nautilus 70B v1d needs about 45.7 GB of memory at Q4_K_M (a 42.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 4 quants, from 23.6 GB (Q3_K_M) to 66.1 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
Nautilus 70B v1d is a 70.6B-parameter Nautilus model in GGUF format, quantized by BeaverAI. Its trained context length is 128K tokens. The repository has 4 quant files, from 23.6 GB (Q3_K_M) to 66.1 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 23.6 GB | 26.8 GB | Too big | Get file → | |
| Q4_K_M | 42.5 GB | 45.7 GB | Too big | Get file → | |
| Q5_K_M | 49.9 GB (2 parts) | 53.1 GB | Too big | Get file → | |
| Q8_0 | 66.1 GB (2 parts) | 69.3 GB | Too big | Get file → |
What GPU do you need for Nautilus 70B v1d?
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 Q3_K_M (23.6 GB file, about 26.8 GB in use).
- 48 GB VRAM: the best quant that fits is Q4_K_M (42.5 GB file, about 45.7 GB in use).
Which Nautilus 70B v1d quant should you choose?
Q4_K_M is the usual starting point for Nautilus 70B v1d: it balances file size and quality well. Here it is a 42.5 GB file.
The Q8_0 file is 66.1 GB, about 1.6 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 Q3_K_M at 23.6 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Nautilus 70B v1d
How much VRAM does Nautilus 70B v1d need?
About 45.7 GB at Q4_K_M with an 8K context window. That is the 42.5 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 Nautilus 70B v1d on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 26.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Nautilus 70B v1d GGUF?
It depends on the quant: Q3_K_M is 23.6 GB, Q4_K_M is 42.5 GB, Q5_K_M is 49.9 GB, Q8_0 is 66.1 GB.
What context length does Nautilus 70B v1d support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.
Where can I download Nautilus 70B v1d GGUF?
The files are on Hugging Face in the BeaverAI/Nautilus-70B-v1d-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.