What AI models can the NVIDIA RTX Spark N1X (5120-core GPU) (32 GB) run?

Unified memory: 32.0 GB
Usable for models: 16.0 GB
Memory bandwidth: 300 GB/s
FP16 compute: 24.0 TFLOPS
Released: 2026

455 / 619 LLMs run Best: Gemma 4 26B-A4B 55 / 60 Image models run Best: FLUX 3 Image Klein 17 / 43 Video models run Best: LTX-Video 2B 66 / 70 Decision models run Best: Jina Reranker v3.5

macOS lets the GPU use roughly two-thirds to three-quarters of unified memory by default, so we plan around that figure rather than the full 32.0 GB.

More about this hardware

Maker	NVIDIA
Type	Unified-memory system on a chip
GPU share of memory	50% (what the GPU can typically be given for a model)
Chip	NVIDIA RTX Spark N1X (5120-core GPU)

Apps that run models well on the NVIDIA RTX Spark N1X (5120-core GPU) (32 GB)

Linux

For a typical model that fits in memory. Each model page picks the best app for that model on this hardware. All apps

5 products with the NVIDIA RTX Spark N1X (5120-core GPU) (32 GB)

Surface Laptop UltraMicrosoft · Laptop · 24, 32, 48 or 128 GBProduct page (opens in a new tab)
Pro 9n 15"Lenovo · Laptop · 32 or 64 GBProduct page (opens in a new tab)
Yoga 9n 2-in-1 16"Lenovo · Laptop · 32 or 64 GBProduct page (opens in a new tab)
OmniBook X14 (RTX Spark)HP · Laptop · 32, 64 or 128 GBProduct page (opens in a new tab)
XPS 16 Creator EditionDell · Laptop · 32 GBProduct page (opens in a new tab)

Best LLMs for the NVIDIA RTX Spark N1X (5120-core GPU) (32 GB)

Quality	Model	Quant	Memory	Speed	Runs
77Great quality (A) · 77 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.	Gemma 4 26B-A4BGoogle	`Q3_K_M`	14.9 GB	89.1 tok/s	Runs welltight fit
78Great quality (A) · 78 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.	Gemma 4 12BGoogle	`Q4_K_M`	9.8 GB	30.8 tok/s	Runs great
76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	K2 Horizon 7BInstitute of Foundation Models	`Q4_K_M`	8.6 GB	40.9 tok/s	Runs great
70Great quality (A) · 70 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	Nemotron 3.5 Bolt E4BNVIDIA	`Q8_0`	10.5 GB	41.7 tok/s	Runs great
69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	Mellum2.1 Thinking (12B-A2.5B)JetBrains	`Q6_K`	12.0 GB	74.7 tok/s	Runs great
68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	Gemma 4 E4BGoogle	`Q8_0`	10.5 GB	41.7 tok/s	Runs great
70Great quality (A) · 70 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	gpt-oss 20BOpenAI	`MXFP4`	14.0 GB	80.0 tok/s	Runs welltight fit
74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.	SenseNova Loop 9B PreviewSenseTime	`Q4_K_M`	8.2 GB	38.1 tok/s	Runs great
74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.	MiMo V2.6 Distill Qwen 9BXiaomi	`Q4_K_M`	7.9 GB	39.1 tok/s	Runs great
73Great quality (A) · 73 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.	Ornith 1.5 9BDeepReinforce	`Q4_K_M`	8.0 GB	38.2 tok/s	Runs great
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	ERNIE 4.5 21B-A3B ThinkingBaidu	`Q4_K_M`	15.7 GB	86.9 tok/s	Runs welltight fit
66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	Maple Preview (20B-A1B)DeepGrove	`Q4_K_M`	14.3 GB	135 tok/s	Runs welltight fit

Best Image models for the NVIDIA RTX Spark N1X (5120-core GPU) (32 GB)

Quality	Model	Quant	Memory	Speed	Runs
89Excellent quality (A+) · 89 of 100: how capable the model is at FP8, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.	FLUX 3 Image KleinBlack Forest Labs	`FP8`	12.4 GB	13 s	Runs great
83Great quality (A) · 83 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	Z-Image TurboAlibaba (Tongyi)	`Q8 GGUF`	13.0 GB	7.3 s	Runs great
84Great quality (A) · 84 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking.	ERNIE-Image TurboBaidu	`Q8 GGUF`	15.0 GB	9.3 s	Runs welltight fit
77Great quality (A) · 77 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking.	FLUX.2 [klein] 4BBlack Forest Labs	`Q8 GGUF`	10.5 GB	2.9 s	Runs great
83Great quality (A) · 83 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.	FLUX.2 [klein] 9BBlack Forest Labs	`Q8 GGUF`	12.3 GB	5.5 s	Runs greatencoder unloaded after use
80Great quality (A) · 80 of 100: how capable the model is at FP8, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	Z-ImageAlibaba (Tongyi)	`FP8`	12.6 GB	39 s	Runs well

Best Video models for the NVIDIA RTX Spark N1X (5120-core GPU) (32 GB)

Quality	Model	Quant	Memory	Speed	Runs
49Fair quality (C) · 49 of 100: how capable the model is at FP8, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.	LTX-Video 2BLightricks	`FP8`	10.8 GB	57 s	Runs great
44Fair quality (C) · 44 of 100: how capable the model is at FP8, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.	CogVideoX 2BZhipu AI	`FP8`	11.0 GB	2.3 min	Runs great
53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.	Wan 2.1 T2V 1.3BAlibaba	`FP8`	12.8 GB	9.1 min	Runs well
53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.	CogVideoX 5BZhipu AI	`FP8`	14.3 GB	6.8 min	Runs welltight fit
53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.	CogVideoX 5B I2VZhipu AI	`FP8`	14.9 GB	6.8 min	Runs welltight fit

Best Decision models for the NVIDIA RTX Spark N1X (5120-core GPU) (32 GB)

Quality	Model	Quant	Memory	Speed	Runs
86Excellent quality (A+) · 86 of 100: how capable the model is at F16, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.	Jina Reranker v3.5Jina AI	`F16`	3.3 GB	29 ms	Runs great
90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3 Reranker 4BAlibaba	`Q8_0`	6.4 GB	145 ms	Runs well
84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	Intern-Decision 4BShanghai AI Lab	`Q8_0`	6.8 GB	95 ms	Runs great
84Great quality (A) · 84 of 100: how capable the model is at F16, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	Jina Reranker v3Jina AI	`F16`	3.3 GB	29 ms	Runs great
88Excellent quality (A+) · 88 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	zerank-2ZeroEntropy	`Q8_0`	6.4 GB	145 ms	Runs well
82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	d1 3BLiquid AI	`F16`	8.2 GB	86 ms	Runs great
82Great quality (A) · 82 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	mxbai-rerank-large v2Mixedbread	`F16`	5.0 GB	67 ms	Runs great
86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	Shieldstral 1.0 3BMistral AI	`Q8_0`	6.2 GB	139 ms	Runs well

Best LLMs by task on this hardware Open in Model Finder

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.