RTX Spark N1X

NVIDIA · 128 GB

6 models6 model configurations6 exact recipes

Model configurations

Each card is a model and hardware setup, including any documented host RAM, storage or CPU requirements. Select a recipe to update its speeds, context and exact command.

Search configurations

Sort by

6 configurations · 6 recipes

gemma-4-12B-it-AWQ-INT4

RTX Spark N1X128 GB1 card per machine · 1 machine

vLLMFormat not recorded

47.7decode tok/s

546prefill tok/s

128Kcontext

Tested on this card · Oct 15, 2026

Full recipe ›

gemma-4-26B-A4B-it-AWQ-4bit

RTX Spark N1X128 GB1 card per machine · 1 machine

vLLMFormat not recorded

64decode tok/s

325prefill tok/s

256Kcontext

Tested on this card · Oct 15, 2026

Full recipe ›

gemma-4-26B-A4B-it-AWQ-8bit

RTX Spark N1X128 GB1 card per machine · 1 machine

vLLMFormat not recorded

52.1decode tok/s

327prefill tok/s

256Kcontext

Tested on this card · Oct 15, 2026

Full recipe ›

gemma-4-31B-it-AWQ-4bit

RTX Spark N1X128 GB1 card per machine · 1 machine

vLLMFormat not recorded

28.3decode tok/s

82prefill tok/s

256Kcontext

Tested on this card · Oct 15, 2026

Full recipe ›

Qwen3.8-27B-AWQ-BF16-INT4

RTX Spark N1X128 GB1 card per machine · 1 machine

vLLMFormat not recorded

15.7decode tok/s

330prefill tok/s

256Kcontext

Tested on this card · Oct 15, 2026

Full recipe ›

Qwen3.8-27B-AWQ-FP8

RTX Spark N1X128 GB1 card per machine · 1 machine

vLLMFP8

23.8decode tok/s

329prefill tok/s

256Kcontext

Tested on this card · Oct 15, 2026

Full recipe ›

Speeds are the selected recipe’s recorded measurements, not estimates; “—” means unmeasured. Evidence distinguishes checks on this card, sibling-card checks, earlier checks and publisher reports.