ricursiveAI.Ripple 65B Preview needs about 42.0 GB of memory at F16 (a 38.8 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 6 quants, from 23.7 GB (F16) to 68.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
ricursiveAI.Ripple 65B Preview is a 64.8B-parameter Ripple model in GGUF format, quantized by DevQuasar. Its trained context length is 2048K tokens. The repository has 6 quant files, from 23.7 GB (F16) to 68.8 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F16 | 23.7 GB | 26.9 GB | Too big | Get file → | |
| F16 | 31.0 GB | 34.2 GB | Too big | Get file → | |
| F16 | 38.8 GB | 42.0 GB | Too big | Get file → | |
| F16 | 45.8 GB | 48.9 GB | Too big | Get file → | |
| F16 | 53.2 GB (4 parts) | 56.3 GB | Too big | Get file → | |
| F16 | 68.8 GB (5 parts) | 72.0 GB | Too big | Get file → |
What GPU do you need for ricursiveAI.Ripple 65B Preview?
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 F16 (23.7 GB file, about 26.9 GB in use).
- 48 GB VRAM: the best quant that fits is F16 (38.8 GB file, about 42.0 GB in use).
Which ricursiveAI.Ripple 65B Preview quant should you choose?
F16 (38.8 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
If memory is tight, the smallest file is F16 at 23.7 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about ricursiveAI.Ripple 65B Preview
How much VRAM does ricursiveAI.Ripple 65B Preview need?
About 42.0 GB at F16 with an 8K context window. That is the 38.8 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 ricursiveAI.Ripple 65B Preview on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 26.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of ricursiveAI.Ripple 65B Preview GGUF?
It depends on the quant: F16 is 23.7 GB, F16 is 31.0 GB, F16 is 38.8 GB, F16 is 45.8 GB, F16 is 53.2 GB, F16 is 68.8 GB.
What context length does ricursiveAI.Ripple 65B Preview support?
The GGUF header lists a trained context length of 2,097,152 tokens (2048K). 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 ricursiveAI.Ripple 65B Preview GGUF?
The files are on Hugging Face in the DevQuasar/ricursiveAI.Ripple-65B-Preview-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 ricursiveAI.Ripple 65B Preview use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.