More
Submit build

Builds / Nvidia RTX Spark N1X, 6,144-core Blackwell GPU (unified)

Surface Laptop Ultra (RTX Spark N1X, 128 GB): 8 models on llama.cpp b12110, Flint 104.8 tok/s, gpt-oss 120B 64.2, Qwen3.8 27B 16.5 (maruhana)

Last updated:

Source: dev.to β†—πŸ“ How measured: reported by the original source; RigBase re-checked the numbers at that source
GPU(s)
Nvidia RTX Spark N1X, 6,144-core Blackwell GPU (unified)
VRAM / unified memory (GB)
82
CPU
Nvidia RTX Spark N1X, 20-core Grace CPU
Amazon Β· eBay (used) Β· Newegg
Motherboard
Microsoft Surface Laptop Ultra
Amazon Β· eBay (used) Β· Newegg
RAM
128 GB unified, 83,968 MiB assigned to the GPU
PSU
not stated
Other
Windows 11 Arm64; llama.cpp b12110 CUDA build; other GPU workloads stopped during measurement
Reported total cost
not stated
Power
not stated

Measured speed (generation tokens/sec)

ModelQuantEnginetok/sPrompt processing (tok/s)Details
Flint 40B-A2.5BNVFP4 (22.9 GB)llama.cpp b12110 (CUDA, Windows on Arm)104.82,066 @ 512-token prompt
est. TTFT @8k β‰ˆ 4.0 s (calculated from measured prefill)
context: llama-benchπŸ“ llama-bench tg128, mean of 3 runs (std dev 0.7 or less), -ngl 999 -fa 1, speculative decoding off; reading a 32,768-token prompt 1,582 tok/s (1 run)
Qwen3.6 35B-A3BUD-Q4_K_M (22.1 GB)llama.cpp b12110 (CUDA, Windows on Arm)75.73,092 @ 512-token prompt
est. TTFT @8k β‰ˆ 2.6 s (calculated from measured prefill)
context: llama-benchπŸ“ llama-bench tg128, mean of 3 runs (std dev 0.7 or less), -ngl 999 -fa 1, speculative decoding off; reading a 32,768-token prompt 2,138 tok/s (1 run); 4 requests at once 110.0 total
gpt-oss 120BMXFP4 (63.4 GB)llama.cpp b12110 (CUDA, Windows on Arm)64.22,116 @ 512-token prompt
est. TTFT @8k β‰ˆ 3.9 s (calculated from measured prefill)
context: llama-benchπŸ“ llama-bench tg128, mean of 3 runs (std dev 0.7 or less), -ngl 999 -fa 1, speculative decoding off; reading a 32,768-token prompt 1,708 tok/s (1 run)
Nemotron 3.5 Bolt 74B-A9BNVIDIA 24GB GGUF, experts IQ2_XXS (22.0 GB)llama.cpp b12110 (CUDA, Windows on Arm)42.71,174 @ 512-token prompt
est. TTFT @8k β‰ˆ 7.0 s (calculated from measured prefill)
context: llama-benchπŸ“ llama-bench tg128, mean of 3 runs (std dev 0.7 or less), -ngl 999 -fa 1, speculative decoding off; reading a 32,768-token prompt 1,083 tok/s (1 run); with the official LiLiCorr drafter (--spec-type draft-dflash, 7 drafts) short answers ran at 105-115 tok/s, longer Japanese answers 55; 4 requests at once 87.1 total
Nemotron 3.5 Super VL 120B-A12BUD-Q3_K_XL (65.8 GB)llama.cpp b12110 (CUDA, Windows on Arm)26.6635 @ 512-token prompt
est. TTFT @8k β‰ˆ 12.9 s (calculated from measured prefill)
context: llama-benchπŸ“ llama-bench tg128, mean of 3 runs (std dev 0.7 or less), -ngl 999 -fa 1, speculative decoding off; reading a 32,768-token prompt 596 tok/s (1 run); UD-Q4_K_XL (86.9 GB) also ran fully offloaded at 23.9 (pp512 625.1, 1 run)
Qwen3.8 27BUD-Q4_K_M (16.5 GB)llama.cpp b12110 (CUDA, Windows on Arm)16.5942 @ 512-token prompt
est. TTFT @8k β‰ˆ 8.7 s (calculated from measured prefill)
context: llama-benchπŸ“ llama-bench tg128, mean of 3 runs (std dev 0.7 or less), -ngl 999 -fa 1, speculative decoding off; reading a 32,768-token prompt 836 tok/s (1 run)
Mistral Small 3.2 24B legacyQ4_K_M (14.3 GB)llama.cpp b12110 (CUDA, Windows on Arm)18.51,183 @ 512-token prompt
est. TTFT @8k β‰ˆ 6.9 s (calculated from measured prefill)
context: llama-benchπŸ“ llama-bench tg128, mean of 3 runs (std dev 0.7 or less), -ngl 999 -fa 1, speculative decoding off; reading a 32,768-token prompt 952 tok/s (1 run)
Hermes 4.3 36B legacyQ4_K_M (21.8 GB)llama.cpp b12110 (CUDA, Windows on Arm)12.0733 @ 512-token prompt
est. TTFT @8k β‰ˆ 11.2 s (calculated from measured prefill)
context: llama-benchπŸ“ llama-bench tg128, mean of 3 runs (std dev 0.7 or less), -ngl 999 -fa 1, speculative decoding off; reading a 32,768-token prompt 393 tok/s (1 run)

Prompt processing = prefill speed (how fast the prompt is read) as reported by the source, with the prompt length it was measured at; blank = the source does not report it. est. TTFT @8k is calculated from the measured prefill speed (8,192 Γ· prefill tok/s), shown only when prefill was measured on a prompt of 512+ tokens. It is not a measurement and ignores load time and caching. measured TTFT is the source's own time-to-first-token. Why prefill matters for coding assistants.

Owner-run test by maruhana (dev.to, 14 Nov 2026; English adaptation of their Zenn article), same build and commands for all 8 models; quantization was not aligned across models. A config-fixing agent task was solved by 6 of 8 models (Flint and Hermes 4.3 did not fix it in 12 steps). Compare with Micro Center's Surface Laptop Ultra numbers (Qwen3.8 27B 14.5).

Source: https://dev.to/maruhana/a-120b-model-ran-about-4x-faster-than-a-27b-one-8-local-llms-on-a-surface-laptop-ultra-5cpg

Blank fields = not stated in the source. We never estimate build data; GPU street prices above are separately sourced and dated.

Embed this result

Copy into a README or blog. Links back to this build. See badge docs (CC BY 4.0 attribution). The SVG does not invent speeds β€” numbers stay on the build page.

Markdown

[![Measured on RigBase](https://getrigbase.com/badge/surface-laptop-ultra-rtx-spark-n1x-8-models-llamacpp-maruhana.svg)](https://getrigbase.com/builds/surface-laptop-ultra-rtx-spark-n1x-8-models-llamacpp-maruhana/)

HTML

<a href="https://getrigbase.com/builds/surface-laptop-ultra-rtx-spark-n1x-8-models-llamacpp-maruhana/" rel="noopener"><img src="https://getrigbase.com/badge/surface-laptop-ultra-rtx-spark-n1x-8-models-llamacpp-maruhana.svg" alt="Measured on RigBase" height="20"/></a>

Preview: Measured on RigBase Β· How to use

Rent before you buy: try this model on a cloud GPU for a few dollars first: Runpod (referral link; sign up with Google to get the new-user bonus)

Quick answers: Can RTX Spark N1X run Flint 40B-A2.5B? Β· Can RTX Spark N1X run Nemotron 3.5 Bolt 74B-A9B? Β· Can RTX Spark N1X run Nemotron 3.5 Super VL 120B-A12B? Β· Can RTX Spark N1X run Qwen3.6 35B-A3B? Β· Can RTX Spark N1X run Qwen3.8 27B? Β· Can RTX Spark N1X run gpt-oss 120B?