What AI models can the Marvell OCTEON TX2 CN9130 NAS (32 GB) run?

RAM: 32.0 GB
Usable for models: 26.2 GB
Memory bandwidth: 19 GB/s
Runs models on: CPU cores
Released: 2019

464 / 622 LLMs run Best: Qwen3.8 27B 58 / 61 Image models run Best: Krea 2 Turbo 37 / 43 Video models run Best: Bernini-R A14B (video generation + editing) 67 / 70 Decision models run Best: Qwen3 Reranker 4B

A NAS with this chip runs models on its processor cores, so memory speed sets the pace: small models (about 1-4B) answer at a usable speed, bigger ones are slow. We plan around 26.2 GB for models, what is left after the NAS system and its storage services. Models run in a container (Docker) or the maker’s app store, and speeds assume the NAS isn’t busy with storage work.

More about this hardware

Maker	Marvell
Type	NAS (network attached storage) processor
Share of memory for models	82% (what the NAS system and its storage services typically leave free at this size)
Chip	Marvell OCTEON TX2 CN9130
AI accelerator	None. Models run on the processor cores.
NAS models with this chip	QNAP TS-435XeU
Memory type	System RAM, shared with the NAS operating system and its storage services
Bandwidth figure	19.2 GB/s, estimated, see the note below
Note	One profile for every NAS built on this chip. Memory speed is an estimate from the chip’s supported memory in a typical NAS fitting; a unit with one memory module runs slower than one with two. Speed assumes the NAS is not busy with storage work.
Specifications	www.qnap.com

Apps that run models well on the Marvell OCTEON TX2 CN9130 NAS (32 GB)

Linux on ARM boards

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

1 product with the Marvell OCTEON TX2 CN9130 NAS (32 GB)

TS-435XeUQNAP · NAS · 4 or 32 GBProduct page (opens in a new tab)

Best LLMs for the Marvell OCTEON TX2 CN9130 NAS (32 GB)

Quality	Model	Quant	Memory	Speed	Runs
94Excellent quality (A+) · 94 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3.8 27BAlibaba	`Q6_K`	26.0 GB	0.2 tok/s	Very slowtight fit
93Excellent quality (A+) · 93 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3.6 27BAlibaba	`Q6_K`	26.0 GB	0.2 tok/s	Very slowtight fit
92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3.5 27BAlibaba	`Q6_K`	26.0 GB	0.2 tok/s	Very slowtight fit
90Excellent quality (A+) · 90 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	Nanbeige4.3 33BBOSS Zhipin (Nanbeige)	`Q4_K_M`	24.6 GB	0.2 tok/s	Very slowtight fit
87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.	Muse Glimmer 30BMeta	`Q4_K_M`	21.0 GB	0.3 tok/s	Very slow
89Excellent quality (A+) · 89 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.	TMax 27BAi2	`Q6_K`	25.7 GB	0.2 tok/s	Very slowtight fit
78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3.6 35B-A3BAlibaba	`Q3_K_M`	20.5 GB	3.5 tok/s	Slow
78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.	MiniCPM-V 4.7 35B-A3BOpenBMB	`Q3_K_M`	20.1 GB	3.5 tok/s	Slow
78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3.5 35B-A3BAlibaba	`Q3_K_M`	20.5 GB	3.5 tok/s	Slow
87Excellent quality (A+) · 87 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.	Fara 1.5 27BMicrosoft	`Q6_K`	25.7 GB	0.2 tok/s	Very slowtight fit
77Great quality (A) · 77 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.	Nex N2 Mini (35B-A3B)Nex-AGI	`Q3_K_M`	20.1 GB	3.5 tok/s	Slow
86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.	Gemma 4 31BGoogle	`Q4_K_M`	23.4 GB	0.3 tok/s	Very slowtight fit

Best Image models for the Marvell OCTEON TX2 CN9130 NAS (32 GB)

Quality	Model	Quant	Memory	Speed	Runs
90Excellent quality (A+) · 90 of 100: how capable the model is at FP8, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	Krea 2 TurboKrea	`FP8`	20.2 GB	26.7 min	Very slow
87Excellent quality (A+) · 87 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.	ERNIE-ImageBaidu	`Q8 GGUF`	18.9 GB	2.9 h	Very slow
83Great quality (A) · 83 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.	FLUX.2 [klein] 9BBlack Forest Labs	`Q8 GGUF`	20.5 GB	14.3 min	Very slow
85Excellent quality (A+) · 85 of 100: how capable the model is at NF4, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.	Ideogram 4Ideogram	`NF4`	21.8 GB	3.2 h	Very slow
90Excellent quality (A+) · 90 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.	FLUX 3 Image KleinBlack Forest Labs	`Q8 GGUF`	12.8 GB	45.3 min	Very slow
78Great quality (A) · 78 of 100: how capable the model is at FP16, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.	FLUX.2 [klein] 4BBlack Forest Labs	`FP16`	18.1 GB	6.9 min	Very slow

Best Video models for the Marvell OCTEON TX2 CN9130 NAS (32 GB)

Quality	Model	Quant	Memory	Speed	Runs
83Great quality (A) · 83 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.	Bernini-R A14B (video generation + editing)ByteDance	`FP8`	20.3 GB	78.4 h	Very slowencoder unloaded after use
70Great quality (A) · 70 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.	Wan 2.2 S2V 14B (speech to video)Alibaba	`Q4 GGUF`	21.6 GB	138.2 h	Very slow
74Great quality (A) · 74 of 100: how capable the model is at FP8, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.	HY-OmniWeaving (8.3B, unified video)Tencent	`FP8`	24.6 GB	54.9 h	Very slowtight fit
68Good quality (B) · 68 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.	Wan 2.1 I2V 14B 480PAlibaba	`Q4 GGUF`	20.6 GB	124.4 h	Very slow
79Great quality (A) · 79 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.	LTX-2.3Lightricks	`Q4 GGUF`	24.5 GB	58.0 h	Very slowtight fit · encoder unloaded after use

Best Decision models for the Marvell OCTEON TX2 CN9130 NAS (32 GB)

Quality	Model	Quant	Memory	Speed	Runs
90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3 Reranker 4BAlibaba	`Q8_0`	7.3 GB	165.6 s	Very slow
90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3 Reranker 8BAlibaba	`Q8_0`	11.7 GB	337.4 s	Very slow
90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.	Skywork Reward V2 Llama 3.1 8BSkywork	`Q8_0`	10.4 GB	667.8 s	Very slow
88Excellent quality (A+) · 88 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.	zerank-2ZeroEntropy	`Q8_0`	7.3 GB	165.6 s	Very slow
86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.	Jina Reranker v3.5Jina AI	`Q8_0`	3.6 GB	24.7 s	Very slow
86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.	Shieldstral 1.0 3BMistral AI	`Q8_0`	7.0 GB	158.6 s	Very slow
84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.	Jina Reranker v3Jina AI	`Q8_0`	3.6 GB	24.7 s	Very slow
84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.	Intern-Decision 4BShanghai AI Lab	`Q8_0`	7.6 GB	94.1 s	Very slow

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.