HP OmniBook Ultra 16 (RTX Spark N1X, 128GB) laptop: local AI benchmarks
| GPU(s) | Nvidia RTX Spark N1X, 6,144-core Blackwell GPU (unified) |
|---|---|
| VRAM / unified memory (GB) | 128 |
| CPU | Nvidia RTX Spark N1X, 20-core Grace CPU Amazon · eBay (used) · Newegg |
| Motherboard | |
| RAM | 128GB LPDDR5X-9400 (64GB GPU / 64GB system split, 62.5GB GPU-usable) Amazon · eBay (used) · Newegg |
| PSU | |
| Other | 2TB Sandisk SN8050S Gen5 SSD; Windows 11 Pro 26H1 (Arm64) |
| Reported total cost | $6,230 (≈€5,559) |
| Power |
Measured speed (generation tokens/sec)
| Model | Quant | Engine | tok/s |
|---|---|---|---|
| Qwen3.6 35B-A3B | Ollama default, 64K context, Codex CLI coding agent | Ollama | 89.5 |
| gpt-oss 20B | Ollama default, 64K context, Codex CLI coding agent | Ollama | 58.0 |
| Llama 3.1 8B | MLPerf Client v2.0 (geomean) | llama.cpp CUDA | 56.5 |
StorageReview review, 16 Oct 2026. Cost is HP.com's configurator price for this 128GB/2TB configuration as of 14 Oct 2026, not a builder's receipt. Generation rates are from an agentic coding task and MLPerf Client, not llama-bench. The 32GB model ran Llama 3.1 8B at the same speed (56.4) but its 12GB GPU split can't load the larger models.
Source: https://www.storagereview.com/review/hp-omnibook-ultra-16-review-rtx-spark-n1x
Blank fields = not stated in the source. We never estimate build data; GPU street prices above are separately sourced and dated.
Rent before you buy: try this model on a cloud GPU for a few dollars first: RunPod
Quick answers: Can RTX Spark N1X run Qwen3.6 35B-A3B? · Can RTX Spark N1X run gpt-oss 20B?