Can I Run SmolLM2 on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM)?

作者： Jakub Rusinowski · 最后更新： 2024年11月20日

Yes — comfortably

Yes, comfortably — SmolLM2 1.7B Instruct at Q8_0 needs about 4.2 GB of the 32 GB usable on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM), leaving ~27.8 GB spare and running at ~238.3 tok/s (estimated), with room for about 8,192 tokens of context.

Confidence: high · Recommended quantization: Q8_0 · Estimated speed: ~238.3 tok/s

Buy This HardwareIntel Arc B570 10GB — 10 GB VRAM · 150 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 5090 Desktop (32 GB VRAM, 64 GB RAM) — what it gives a model

Usable memory for models	32 GB
Memory bandwidth	1792 GB/s
Form factor	Desktop
Operating system	Windows or Linux
Memory upgradeable	Yes

SmolLM2 on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM): memory by quantization

Quant	Memory needed	Fits 32 GB?	Max context	Est. speed	Download
F16	5.8 GB	✓ Yes	8K	~185.5 tok/s	3.4 GB
Q8_0	4.2 GB	✓ Yes	8K	~238.3 tok/s	1.8 GB
Q6_K	3.8 GB	✓ Yes	8K	~257.2 tok/s	1.4 GB
Q5_K_M	3.6 GB	✓ Yes	8K	~266.9 tok/s	1.2 GB
Q4_K_M	3.4 GB	✓ Yes	8K	~276.8 tok/s	1 GB
Q3_K_M	3.1 GB	✓ Yes	8K	~295.2 tok/s	0.7 GB
Q2_K	3 GB	✓ Yes	8K	~306.4 tok/s	0.6 GB

Which SmolLM2 sizes fit

Variant	Needs at Q4_K_M	Fits?	Est. speed
SmolLM2 1.7B Instruct	3.4 GB	✓ Fits	~276.8 tok/s
SmolLM2 360M Instruct	1.4 GB	✓ Fits	~394.7 tok/s

RTX 5090 desktop limitations

575 W board power — budget for a 1000 W+ PSU and the heat it puts into the room.
Models larger than 32 GB must offload to system RAM, which costs roughly an order of magnitude in speed.

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.
32 GB of VRAM on the NVIDIA GeForce RTX 5090 at 1792 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 computed from this model's published attention configuration.

FAQ