RTX Spark N1X for local LLMs

8 measured results from 2 builds, each linked to its source.

Can it run? GLM 4.7 Flash on RTX Spark N1X Muse Glimmer 30B on RTX Spark N1X Nemotron 3 Nano Omni 30B on RTX Spark N1X Qwen3.5 122B on RTX Spark N1X Qwen3.6 35B-A3B on RTX Spark N1X Qwen3.8 27B on RTX Spark N1X gpt-oss 20B on RTX Spark N1X

All builds with the RTX Spark N1X

All measured results

Hide speculative-decoding results ⚡ (MTP, DFlash, DSpark and similar draft-and-verify methods give much higher tok/s on predictable text and are not comparable 1:1 with plain decode)

All RTX Spark N1X builds: see also all GPUs · best LLMs by memory size · download the dataset.

FAQ

How fast is the RTX Spark N1X for local LLMs?

The fastest plain-decode result we have is 89.5 tok/s on Qwen3.6 35B-A3B (Ollama default, 64K context, Codex CLI coding agent, Ollama) in HP OmniBook Ultra 16 (RTX Spark N1X, 128GB) laptop: local AI benchmarks. Speed depends heavily on the model, quant and engine, so compare like with like in the table. RigBase lists 8 measured results from 2 builds.

How much memory does the RTX Spark N1X have?

unified memory.

Which models have been measured on the RTX Spark N1X?

GLM 4.7 Flash, Llama 3.1 8B, Muse Glimmer 30B, Nemotron 3 Nano Omni 30B, Qwen3.5 122B, Qwen3.6 35B-A3B, Qwen3.8 27B, gpt-oss 20B.

Where do these numbers come from?

Every row links to a build page with its original public source (benchmark logs, READMEs, forum posts). RigBase does not re-run the benchmarks. Results marked ⚡ use speculative decoding and are not comparable 1:1 with plain decode.