Can I Run Nemotron Cascade 2 on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)?

Autor: Jakub Rusinowski · Ostatnia aktualizacja: 11 września 2026

Yes, but it is tight

Yes, but it is tight — Nemotron-Cascade 2 30B-A3B at Q4_K_M needs about 21.7 GB of the 24 GB usable on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM), leaving only ~2.3 GB before the runtime starts swapping. Expect ~160.3 tok/s (estimated), with room for about 16,384 tokens of context.

Confidence: low · Recommended quantization: Q4_K_M · Estimated speed: ~160.3 tok/s

Buy This HardwareAMD Radeon RX 7900 XTX 24GB — 24 GB VRAM · 355 W board power Deploy in the Cloud NowRTX 4090 on RunPod — from $0.34/hr · rate checked 2026-07

or compare on Vast.ai from $0.35/hr (typical low · varies)

As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.

RTX 4090 Desktop (24 GB VRAM, 64 GB RAM) — what it gives a model

Usable memory for models	24 GB
Memory bandwidth	1008 GB/s
Form factor	Desktop
Operating system	Windows or Linux
Memory upgradeable	Yes

Nemotron Cascade 2 on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM): memory by quantization

Quant	Memory needed	Fits 24 GB?	Max context	Est. speed	Download
F16	65.8 GB	✗ No	—	—	63.2 GB
Q8_0	36.2 GB	✗ No	—	—	33.6 GB
Q6_K	28.5 GB	✗ No	—	—	25.9 GB
Q5_K_M	25 GB	✗ No	—	—	22.4 GB
Q4_K_M	21.7 GB	✓ Yes	16K	~160.3 tok/s	19.1 GB
Q3_K_M	16.1 GB	✓ Yes	32K	~184.6 tok/s	13.5 GB
Q2_K	13 GB	✓ Yes	32K	~201.4 tok/s	10.4 GB

Which Nemotron Cascade 2 sizes fit

Variant	Needs at Q4_K_M	Fits?	Est. speed
Nemotron Cascade 2 70B (Unverified Listing)	45.4 GB	✗ Too large	—
Nemotron-Cascade 2 30B-A3B	21.7 GB	✓ Fits	~160.3 tok/s

What to watch out for

1 larger variant of Nemotron Cascade 2 does not fit and would need CPU offload or different hardware.
This model does not publish its full attention configuration, so the KV-cache share of these figures is inferred from its parameter count rather than computed exactly.

RTX 4090 desktop limitations

24 GB is the sweet spot for 27–32B models at Q4; 70B needs offload or a second card.

Recommended setup

Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving

How these numbers are calculated

Memory need = quantized weights + KV cache at 8,192 tokens (f16) + 0.8 GB runtime overhead.
24 GB of VRAM on the NVIDIA GeForce RTX 4090 at 1008 GB/s.
64 GB of system RAM available for CPU offload when a model exceeds VRAM.
Throughput is a memory-bandwidth roofline estimate, not a measurement. It is labelled "estimated" everywhere it appears.
KV cache is inferred from the parameter count because this model does not publish its full attention configuration.

FAQ