Cthulhu 70B v1 needs about 30.7 GB of memory at IQ3_XXS (a 27.5 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 4 quants, from 19.1 GB (IQ2_XXS) to 40.0 GB (Q4_0). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
Cthulhu 70B v1 is a 70.6B-parameter Cthulhu model in GGUF format, quantized by Naphula. Its trained context length is 128K tokens. The repository has 4 quant files, from 19.1 GB (IQ2_XXS) to 40.0 GB (Q4_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XXS | 19.1 GB | 22.3 GB | Too big | Get file → | |
| IQ3_XXS | 27.5 GB | 30.7 GB | Too big | Get file → | |
| IQ4_XS | 37.9 GB | 41.1 GB | Too big | Get file → | |
| Q4_0 | 40.0 GB | 43.2 GB | Too big | Get file → |
What GPU do you need for Cthulhu 70B v1?
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_XXS (19.1 GB file, about 22.3 GB in use).
- 32 GB VRAM: the best quant that fits is IQ3_XXS (27.5 GB file, about 30.7 GB in use).
- 48 GB VRAM: the best quant that fits is Q4_0 (40.0 GB file, about 43.2 GB in use).
Which Cthulhu 70B v1 quant should you choose?
IQ3_XXS (27.5 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 IQ2_XXS at 19.1 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 Cthulhu 70B v1
How much VRAM does Cthulhu 70B v1 need?
About 30.7 GB at IQ3_XXS with an 8K context window. That is the 27.5 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 Cthulhu 70B v1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 22.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Cthulhu 70B v1 GGUF?
It depends on the quant: IQ2_XXS is 19.1 GB, IQ3_XXS is 27.5 GB, IQ4_XS is 37.9 GB, Q4_0 is 40.0 GB.
What context length does Cthulhu 70B v1 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 Cthulhu 70B v1 GGUF?
The files are on Hugging Face in the Naphula/Cthulhu-70B-v1-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 Cthulhu 70B v1 use?
Hugging Face lists the license as llama3.3. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.