What GPU do I need to run ricursiveAI/Ripple-65B-Preview-DFlash2?
4.0B parameters, published in BF16. View on Hugging Face
Set up Ripple-65B-Preview-DFlash2Ripple-65B-Preview-DFlash2 is published by ricursiveAI on Hugging Face, with 2,787 downloads and 21 likes to date. It's a DFlash2DraftModel model built for text-generation, published natively in BF16.
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision times a flat 1.2 overhead for activations and fragmentation. The KV-cache grows with context and is not in that factor; it is listed per model below where the architecture is published. Full formula and assumptions: methodology.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 7.5 GB | 9.0 GB | RTX 3060 | 1 | $0.110/hr |
| FP8 (quantized) | 3.8 GB | 4.5 GB | RTX 4070 | 1 | $0.154/hr |
| INT4 (quantized) | 1.9 GB | 2.3 GB | RTX 3060 | 1 | $0.110/hr |
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run Ripple-65B-Preview-DFlash2 at its published (BF16) precision: 1× RTX 3060, at $0.110/hr per GPU ($0.110/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
Ripple-65B-Preview-DFlash2: common questions
Does Ripple-65B-Preview-DFlash2 fit on a 12 GB GPU?
Yes. At BF16 it needs 9.0 GB of VRAM, so a 12 GB card holds it with 3.0 GB to spare. An 8 GB card is not enough for it at BF16.
What is the least VRAM Ripple-65B-Preview-DFlash2 can run in?
2.3 GB, at INT4 (quantized), which fits a 6 GB card, against 9.0 GB at BF16. That row assumes an INT4 checkpoint has actually been published for this model, so check its Hugging Face page before planning around it.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More ricursiveAI models
- Ripple-65B-Preview (64.8B, BF16)
- Ripple-65B-Base-Preview (64.8B, BF16)
Lineage
Based on Ripple-65B-Preview.
More on Ripple-65B-Preview-DFlash2
Fits on a 12 GB GPU at BF16: every model that fits in 12 GB.
Fits on an 8 GB GPU at FP8: every model that fits in 8 GB.
Related reading: H100 pricing and specs, How much VRAM you need for LLMs, and What AI inference is.
