More
Submit build

Can RTX 3090 run Ripple 65B Preview?

Last updated:

Probably only partly: the weights are larger than its memory, so part of the model likely ran from system RAM. Measured 25.9 tok/s generation with part of the model offloaded to system RAM (llama.cpp b12167 llama-server (CUDA), AD-IQ2_XXS (AtomicChat GGUF, 20.0 GB); source).

Every measured result for Ripple 65B Preview on RTX 3090

BuildQuant / setupEnginetok/s
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)AD-IQ2_XXS (AtomicChat GGUF, 20.0 GB)llama.cpp b12167 llama-server (CUDA)25.9 CPU offloadsource

Memory: RTX 3090 has 24 GB. Ripple 65B Preview weights are about 39.8 GB at Q4_K_M (65B params × 4.89 bits ÷ 8, before context/KV cache). Arithmetic, not a measurement; long contexts need more. Check other quants in the VRAM calculator.

Speeds are decode (generation) tokens/sec as reported by each source; quant, engine and context differ, so small gaps are noise.

All measured speeds for Ripple 65B Preview: best home rig for Ripple 65B Preview.

Ripple 65B Preview on other hardware: 4x Intel Arc Pro B70 · Apple M3 Ultra

Other models measured on RTX 3090: DeepSeek R1 671B · Flint 40B-A2.5B · GLM 4.7 Flash · Gemma 4 31B · Inkling 2 Mini · Nemotron 3.5 Bolt 74B-A9B · Nemotron 3.5 Lightning 30B-A3B · Qwen3.6 27B · Qwen3.6 35B-A3B · Qwen3.8 27B · gpt-oss 120B · gpt-oss 20B

Not enough VRAM? Rent before you buy. Run Ripple 65B Preview on a bigger GPU on a rented 24–96 GB cloud GPU by the hour and see the real speed before spending €1,000+. Try it on Runpod
Referral link: if you sign up with Google and add $10, Runpod gives you and RigBase bonus credit (terms). It never affects our data.