RI

Ripple-65B-Preview

RippleGGUF by webmp3Updated 2026-11-07
Download on Hugging Face
Parameters64.8B
Context2048K
Layers80
Architecturericursive
Smallest quant23.7 GB
Quick answer

Ripple-65B-Preview needs about 42.0 GB of memory at Q4_K_M (a 38.8 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 4 quants, from 23.7 GB (Q2_K) to 45.8 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

Ripple-65B-Preview is a 64.8B-parameter Ripple model in GGUF format, quantized by webmp3. Its trained context length is 2048K tokens. The repository has 4 quant files, from 23.7 GB (Q2_K) to 45.8 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K23.7 GB 26.9 GB
Too big Get file →
Q3_K_M31.0 GB 34.2 GB
Too big Get file →
Q4_K_M38.8 GB 42.0 GB
Too big Get file →
Q5_K_M45.8 GB 48.9 GB
Too big Get file →

What GPU do you need for 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 Q2_K (23.7 GB file, about 26.9 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_M (38.8 GB file, about 42.0 GB in use).

Which Ripple-65B-Preview quant should you choose?

Q4_K_M is the usual starting point for Ripple-65B-Preview: it balances file size and quality well. Here it is a 38.8 GB file.

If memory is tight, the smallest file is Q2_K at 23.7 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

Architecturericursive
Parameters64.8B
Layers80
Trained context2,097,152 tokens
KV cache (fp16)320 KB per token

Source

Quantized bywebmp3
FamilyRipple
Licenseapache-2.0
Downloads (HF)182
Last updated2026-11-07

Frequently asked questions about Ripple-65B-Preview

How much VRAM does Ripple-65B-Preview need?

About 42.0 GB at Q4_K_M 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 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 Ripple-65B-Preview GGUF?

It depends on the quant: Q2_K is 23.7 GB, Q3_K_M is 31.0 GB, Q4_K_M is 38.8 GB, Q5_K_M is 45.8 GB.

What context length does 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 Ripple-65B-Preview GGUF?

The files are on Hugging Face in the webmp3/Sakura-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 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.

Other GGUFs of Ripple-65B-Preview

Similar models

Browse all →

More from webmp3

All by webmp3 →

More Ripple models

All Ripple →

Other large models

All large models →