<!-- Markdown mirror of https://getrigbase.com/models/ripple-65b-preview/ . Source of truth is the HTML page. Data licence: CC BY 4.0, please cite RigBase (https://getrigbase.com/models/ripple-65b-preview/). -->
Source: https://getrigbase.com/models/ripple-65b-preview/
Last updated: 2026-11-15

[Models](https://getrigbase.com/models/) / Ripple 65B Preview

# Best home rig for Ripple 65B Preview

Quick answer

**How much VRAM does Ripple 65B Preview need?**
The weights are about 39.8 GB at Q4_K_M (65B params × 4.89 bits ÷ 8, before context/KV cache). Add memory for context (KV cache) and the runtime. The smallest-memory setup with a measured result here, fully in memory, is Apple M3 Ultra (96 GB) at 15.0 tok/s.

**What is the fastest measured hardware for Ripple 65B Preview?**
RTX 3090: 25.9 tok/s generation (llama.cpp b12167 llama-server (CUDA), AD-IQ2_XXS (AtomicChat GGUF, 20.0 GB)), from https://inferencekey.com/research/ripple-65b-dense-coder-one-card.

Last updated: 15 Nov 2026

Current model 65B dense 4 measured results fastest plain decode: 25.9 tok/s  [model info ↗](https://huggingface.co/ricursiveAI/Ripple-65B-Preview)

[Will it fit my GPU?](https://getrigbase.com/can-it-run/) [Best value GPU per euro →](https://getrigbase.com/guides/best-value-gpu-local-llm-europe/)

Real, measured generation speeds for Ripple 65B Preview on home hardware, fastest first. Different quants/engines aren't directly comparable.

| Build | Quant | Engine | tok/s | Prompt processing (tok/s) | Cost | Source |
|---|---|---|---|---|---|---|
| [RTX 3090 24 GB: Ripple-65B Preview 2-bit AD-IQ2_XXS on llama.cpp at 23.6-30.9 tok/s (16K ctx, one wrong test in three coding answers)](https://getrigbase.com/builds/rtx-3090-24gb-ripple-65b-preview-ad-iq2xxs-llamacpp-inferencekey/) | AD-IQ2_XXS (AtomicChat GGUF, 20.0 GB) | llama.cpp b12167 llama-server (CUDA) | **25.9** | – |  | [inferencekey.com ↗](https://inferencekey.com/research/ripple-65b-dense-coder-one-card) |
| [Mac Studio M3 Ultra 96 GB: Ripple-65B Preview Q4_K_M on llama.cpp at 15.0 tok/s (13.5 after a 32K prompt, 9.45 at 128K)](https://getrigbase.com/builds/mac-studio-m3-ultra-96gb-ripple-65b-preview-q4km-llamacpp-leanzero/) | Q4_K_M (self-quantized, 38.8 GB) | llama.cpp (Metal) | **15.0** | 126 @512 · est. TTFT @8k ≈65.1 s* |  | [leanzero.net ↗](https://leanzero.net/blog/ripple-65b-preview-benchmark-lfm3-1-7b) |
| [RTX A6000 48 GB: Ripple-65B Preview (dense 65B coder) Q4_K_M on llama.cpp at 14.3-16.3 tok/s, prompts up to 256K on one card](https://getrigbase.com/builds/rtx-a6000-48gb-ripple-65b-preview-q4km-llamacpp-inferencekey/) | Q4_K_M (AtomicChat GGUF, 38.8 GB) | llama.cpp b12167 llama-server (CUDA) | **14.4** | 540 @25,930 · est. TTFT @8k ≈15.2 s* |  | [inferencekey.com ↗](https://inferencekey.com/research/ripple-65b-dense-coder-one-card) |
| [4x Intel Arc Pro B70 (Xeon workstation): Ripple-65B Preview Q4_K_M on llama.cpp SYCL at 13.0 tok/s, layer split, 200K context](https://getrigbase.com/builds/4x-arc-pro-b70-xeon-ripple-65b-preview-q4km-sycl-intelinside/) | Q4_K_M (AtomicChat GGUF, 38.8 GB) | llama.cpp b12314 (SYCL), layer split across 4 GPUs | **13.0** | – |  | [intelinside.ai ↗](https://www.intelinside.ai/results/335) |

Prompt processing = prefill speed reported by the source, @ prompt length. * est. TTFT @8k is calculated from measured prefill, not measured. [Why it matters](https://getrigbase.com/can-it-run/#prefill).

## Quality cost of each quant for Ripple 65B Preview

How far each quantization drifts from the full-precision (BF16) model, as published by the quant maker. Lower KL divergence (KLD) is closer to the original; same-top-token % is how often the quant picks the same next token as BF16. Q4_K_M is usually the sweet spot; below Q4 the drift grows fast, which is why RigBase only lists Q4-or-higher speed results.

| Quant | File size | Mean KLD vs BF16 | Same top token |
|---|---|---|---|
| Q8_0 | 68.8 GB | **0.001** | 99.0% |
| AD-Q6_K | 57.7 GB | **0.0016** | 98.7% |
| AD-Q5_K_M | 47.9 GB | **0.0067** | 97.3% |
| AD-Q4_K_M | 40.4 GB | **0.0136** | 95.9% |
| AD-IQ4_XS | 38.7 GB | **0.0149** | 95.6% |
| Q4_K_M (plain llama.cpp, no imatrix) | 38.8 GB | **0.038** | 93.0% |
| AD-IQ3_S below Q4 | 32.4 GB | **0.0327** | 93.4% |
| AD-IQ3_XXS below Q4 | 28.0 GB | **0.0584** | 91.2% |
| AD-IQ2_S below Q4 | 25.3 GB | **0.0959** | 88.5% |
| AD-IQ2_XS below Q4 | 22.1 GB | **0.1778** | 84.2% |
| AD-IQ2_XXS below Q4 | 20.0 GB | **0.2605** | 80.8% |
| AD-IQ1_M below Q4 | 18.5 GB | **0.3743** | 76.8% |

Source: [huggingface.co ↗](https://huggingface.co/AtomicChat/Ripple-65B-Preview-GGUF). AtomicChat (quant publisher) GGUF card: llama-perplexity on their 30-language neutral corpus (87 chunks of 4,096 tokens), llama.cpp 9e2a04a with the Ripple port, vs the BF16 original. AD files are AtomicChat's imatrix per-tensor layouts; the plain Q4_K_M is a no-imatrix baseline. KLD from different publishers, datasets or llama.cpp builds isn't directly comparable.
Ad · this space is available **Sponsor this spot: reach people building local AI rigs.** One clearly-labeled slot per page, no tracking scripts.  [Sponsor this spot →](https://getrigbase.com/advertise/#inquiry)

**Rent before you buy:** try this model on a cloud GPU for a few dollars first: [Runpod](https://runpod.io?ref=77qcpl2c) (referral link; sign up with Google to get the new-user bonus)

## Memory math: how much VRAM / RAM does Ripple 65B Preview need?

Ripple 65B Preview has **65B parameters** ([source](https://huggingface.co/ricursiveAI/Ripple-65B-Preview): Ricursive model card: dense 65B, 80 layers (64 sliding-window + 16 global), Apache 2.0, released 4 Nov 2026). Weight size = parameters × bits-per-weight ÷ 8, before context (KV cache) and runtime overhead.

| Format | Bits/weight | Weights | Smallest common memory size that holds the weights alone |
|---|---|---|---|
| Q8_0 | 8.50 | 69.1 GB | 96 GB |
| Q6_K | 6.56 | 53.3 GB | 64 GB |
| Q5_K_M | 5.70 | 46.3 GB | 48 GB |
| Q4_K_M | 4.89 | **39.8 GB** | 48 GB |
| Q3_K_M | 4.00 | 32.5 GB | 48 GB |
| Q2_K | 3.16 | 25.7 GB | 32 GB |

Bits-per-weight for GGUF quants are llama.cpp's own figures ([llama.cpp quantize README](https://github.com/ggml-org/llama.cpp/blob/master/tools/quantize/README.md)). "As measured" rows apply the source's stated bits-per-weight to the parameter count; real files differ slightly because some layers stay at higher precision. Try other combinations in the [VRAM calculator](https://getrigbase.com/can-it-run/).

**Measured on setups with less GPU memory than the Q4_K_M weights** (so part of the model lived in system RAM or was streamed from disk):

- [RTX 3090 (24 GB)](https://getrigbase.com/builds/rtx-3090-24gb-ripple-65b-preview-ad-iq2xxs-llamacpp-inferencekey/): **25.9 tok/s** (AD-IQ2_XXS (AtomicChat GGUF, 20.0 GB))

## FAQ

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

The weights are about 39.8 GB at Q4_K_M (65B params × 4.89 bits ÷ 8, before context/KV cache). Add memory for context (KV cache) and the runtime. The smallest-memory setup with a measured result here, fully in memory, is Apple M3 Ultra (96 GB) at 15.0 tok/s.

### What is the fastest measured hardware for Ripple 65B Preview?

RTX 3090: 25.9 tok/s generation (llama.cpp b12167 llama-server (CUDA), AD-IQ2_XXS (AtomicChat GGUF, 20.0 GB)), from https://inferencekey.com/research/ripple-65b-dense-coder-one-card.

### Which GPUs have measured results for Ripple 65B Preview?

4x Intel Arc Pro B70, Apple M3 Ultra, RTX 3090.

**Can it run on…** [4x Intel Arc Pro B70](https://getrigbase.com/can-i-run/ripple-65b-preview-on-4x-intel-arc-pro-b70/) · [Apple M3 Ultra](https://getrigbase.com/can-i-run/ripple-65b-preview-on-apple-m3-ultra/) · [RTX 3090](https://getrigbase.com/can-i-run/ripple-65b-preview-on-rtx-3090/)

Related: [what GPU do you need for 2026 models](https://getrigbase.com/guides/what-gpu-for-qwen3-6-gemma-4-gpt-oss/) · [all builds](https://getrigbase.com/builds/)

**Search answer:** [How much VRAM do you need for Ripple 65B Preview?](https://getrigbase.com/vram/ripple-65b-preview/) · [Will it fit my GPU?](https://getrigbase.com/can-it-run/)
