estimate

Can I run NVIDIA Nemotron 3.5 Super VL on a Dual RTX 3090?

Only with CPU offload (slow) (estimate)

speed: not estimated for MoE yet

Can I run NVIDIA Nemotron 3.5 Super VL on a Dual RTX 3090? Only with CPU offload (slow) (estimate). About 72.7 GB at Q4_K_M (estimate).

VRAM per quant for NVIDIA Nemotron 3.5 Super VL

Updated . The later of the hardware price date and the formula date.

NVIDIA Nemotron 3.5 Super VL on Dual RTX 3090, formula estimate
QuantContextWeightsKVOverheadTotalUsableFit
Q4 Q4_K_M8,192 tokens71.8 GB measured GGUF file size0.1 GB estimate0.8 GB estimate72.7 GB estimate46.8 GB estimateoffload
Q5 Q5 (~0.71 bytes/param)8,192 tokens85.2 GB estimate0.1 GB estimate0.8 GB estimate86.1 GB estimate46.8 GB estimateoffload
Q8 Q88,192 tokens128.4 GB estimate0.1 GB estimate0.8 GB estimate129.3 GB estimate46.8 GB estimateoffload
FP16 FP168,192 tokens240.0 GB estimate0.1 GB estimate0.8 GB estimate240.9 GB estimate46.8 GB estimateno
Q4, longer context32,768 tokens71.8 GB measured GGUF file size0.3 GB estimate0.8 GB estimate72.9 GB estimate46.8 GB estimateoffload

Formula estimate, not a benchmark. Method →

Cheapest catalog option that fits at Q4

Mac Studio M4 Max 128GB, catalog price, €3,290, dated 2026-10-16. No buy link.

This hardware

$6,054€5,408

price as of 16 Oct 2026

128 GB DDR4 (estimate): $2,754€2,460. From the 16 Oct 2026 fact-check.

rest of system (estimate): $560€500. The total is the GPU price plus the RAM line plus this estimate. It is not a checked system price.

price unverified

GPU line is 2× the used median €1,224 (€2,448), labelled used, from pcprice.watch (https://www.pcprice.watch/gpu-buying-guide/rtx-3090-price-used-and-specs). 128 GB DDR4 (estimate) €2,460, from the 16 Oct 2026 fact-check. Rest of system (estimate) €500. Other parts from €500 in that fact-check. Not a shop listing. The total is the GPU price plus the RAM line plus that rest estimate. It is not a checked system price.

Embed this

NVIDIA Nemotron 3.5 Super VL on Dual RTX 3090

[![NVIDIA Nemotron 3.5 Super VL Q4 on Dual RTX 3090: offload (estimate)](https://localllmrig.com/badge/nemotron-3.5-super-vl/dual-rtx-3090.svg)](https://localllmrig.com/can-i-run/nemotron-3.5-super-vl/dual-rtx-3090?utm_source=badge)

Questions

Can I run NVIDIA Nemotron 3.5 Super VL on a Dual RTX 3090?
Only with CPU offload (slow) (estimate).
How much memory does NVIDIA Nemotron 3.5 Super VL need at Q4?
About 72.7 GB at 8,192 tokens (estimate): 71.8 GB weights (measured GGUF file size), 0.1 GB KV cache, 0.8 GB overhead.
How fast is NVIDIA Nemotron 3.5 Super VL on Dual RTX 3090 (estimate)?
speed: not estimated for MoE yet
NVIDIA Nemotron 3.5 Super VL on Dual RTX 3090 (estimate) · localLLMrig