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

Written by Jakub Rusinowski · Last updated November 20, 2024

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

RTX 5090 Desktop (32 GB VRAM, 64 GB RAM) — what it gives a model

Usable memory for models32 GB
Memory bandwidth1792 GB/s
Form factorDesktop
Operating systemWindows or Linux
Memory upgradeableYes

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

QuantMemory neededFits 32 GB?Max contextEst. speedDownload
F165.8 GB✓ Yes8K~185.5 tok/s3.4 GB
Q8_04.2 GB✓ Yes8K~238.3 tok/s1.8 GB
Q6_K3.8 GB✓ Yes8K~257.2 tok/s1.4 GB
Q5_K_M3.6 GB✓ Yes8K~266.9 tok/s1.2 GB
Q4_K_M3.4 GB✓ Yes8K~276.8 tok/s1 GB
Q3_K_M3.1 GB✓ Yes8K~295.2 tok/s0.7 GB
Q2_K3 GB✓ Yes8K~306.4 tok/s0.6 GB

Which SmolLM2 sizes fit

VariantNeeds at Q4_K_MFits?Est. speed
SmolLM2 1.7B Instruct3.4 GB✓ Fits~276.8 tok/s
SmolLM2 360M Instruct1.4 GB✓ Fits~394.7 tok/s

RTX 5090 desktop limitations

Recommended setup

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

How these numbers are calculated

FAQ

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

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.

Which quantization of SmolLM2 should I use on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM)?

Q8_0 — it needs about 4.2 GB of the 32 GB available, downloads as roughly 1.8 GB, and runs at an estimated 238.3 tokens/sec with up to 8K of context.

What limits SmolLM2 on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM)?

Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.

Which runtime should I use?

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

Other Computers

Other Models on RTX 5090 Desktop (32 GB VRAM, 64 GB RAM)

SmolLM2 on GPUs

What This Model Is Good At

Model & Tools

← Can I Run It? | SmolLM2 model page | Check your hardware