Can RTX Spark N1X run Nemotron 3 Nano Omni 30B?
Yes. Measured 63.9 tok/s generation (llama.cpp (Nvidia ARM64 build), general, short (~90-token) prompt; source).
Every measured result for Nemotron 3 Nano Omni 30B on RTX Spark N1X
| Build | Quant / setup | Engine | tok/s | |
|---|---|---|---|---|
| Microsoft Surface Laptop Ultra (RTX Spark N1X): llama.cpp speeds on 2026 models (Micro Center) | general, short (~90-token) prompt | llama.cpp (Nvidia ARM64 build) | 63.9 | source |
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 Nemotron 3 Nano Omni 30B: best home rig for Nemotron 3 Nano Omni 30B.
Nemotron 3 Nano Omni 30B on other hardware: DGX Spark (GB10)
Other models measured on RTX Spark N1X: GLM 4.7 Flash · Muse Glimmer 30B · Qwen3.5 122B · Qwen3.6 35B-A3B · Qwen3.8 27B · gpt-oss 20B
Not enough VRAM? Rent before you buy. Run Nemotron 3 Nano Omni 30B 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.
Referral link: if you sign up with Google and add $10, Runpod gives you and RigBase bonus credit (terms). It never affects our data.