Minisforum N5 MAX AI NAS

Configurations

Pick one to see which models it runs. More memory lets larger models fit; bandwidth sets how fast they answer.

Specifications 128 GB configuration

Maker	MMinisforum
Type	NAS
Processor	AMD Ryzen AI Max+ 395 NAS (128 GB)
Memory (RAM)	128 GB
Usable for AI models	96.0 GB
Memory bandwidth	256 GB/s
FP16 compute	59.4 TFLOPS
Runs models on	GPU (Vulkan)
Drive bays	5x 3.5/2.5in SATA (32TB each) + 5x M.2 NVMe (up to 200TB total)
NAS system	MinisCloud OS
Containers (Docker)	Yes
Virtual machines	Yes
Memory upgrade	LPDDR5X unified memory, soldered, 8000 MT/s default (8533 as… · up to 128 GB per the maker · non-ECC
Graphics card options	External GPU: No OCuLink port and no PCIe slot in the maker spec table; has 2x USB4 v2 (80Gbps) and 1x USB4 (40Gbps). Maker….
Notes	AMD Ryzen AI Max+ 395. Strix Halo with up to 128GB unified memory shared with the Radeon 8060S. Maker's own llama.cpp numbers on the 128GB unit: gpt-oss-120b 59.3 tok/s, Qwen3.5-122B-A10B Q4_K_M 31.8 tok/s, gpt-oss-20b 83.1 tok/s, Gemma 4 26B-A4B 70.3 tok/s. Ships with a local agent (MinisOpenClaw) and one-click Docker.
Product page	store.minisforum.com (opens in a new tab)

Running AI on the Minisforum N5 MAX AI NAS

Yes, it runs AI models on the NAS itself. Models run on its GPU (Vulkan), and this configuration leaves about 96.0 GB for them after the NAS system and its storage services. The grades below assume the NAS isn’t busy with backups or media work at the same time. More memory is the upgrade that matters most: see the configurations.

Apps you can install to run models

Apps that run LLMs on a NAS, with their container images

AI features from Minisforum

Best LLMs for the Minisforum N5 MAX AI NAS 128 GB

Quality	Model	Quant	Memory	Speed	Runs
A+90Excellent quality (A+) · 90 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking.	AAKolibri 1 (78B-A3.5B)Aleph Alpha	Q6_K	72.5 GB	45.4 tok/s	Runs great
A+85Excellent quality (A+) · 85 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3 Coder Next (80B-A3B)Alibaba	Q6_K	73.8 GB	51.1 tok/s	Runs great
A+85Excellent quality (A+) · 85 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3-Next 80B-A3B ThinkingAlibaba	Q6_K	75.2 GB	51.1 tok/s	Runs great
A+93Excellent quality (A+) · 93 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3.6 35B-A3BAlibaba	Q8_0	46.6 GB	39.1 tok/s	Runs great
A+93Excellent quality (A+) · 93 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.	Qwen3.5 35B-A3BAlibaba	Q8_0	46.6 GB	39.1 tok/s	Runs great
A+93Excellent quality (A+) · 93 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.	OBMiniCPM-V 4.7 35B-A3BOpenBMB	Q8_0	45.8 GB	39.1 tok/s	Runs great
A84Great quality (A) · 84 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	OAgpt-oss 120BOpenAI	MXFP4	75.2 GB	47.7 tok/s	Runs great
A+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.	RFlint (40B-A2.5B)Recursive	Q8_0	50.7 GB	45.6 tok/s	Runs great
A83Great quality (A) · 83 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3 Next 80B-A3B InstructAlibaba	Q6_K	75.2 GB	51.1 tok/s	Runs great
A+92Excellent quality (A+) · 92 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.	NANex N2 Mini (35B-A3B)Nex-AGI	Q8_0	45.7 GB	39.1 tok/s	Runs great

Best Image models for the Minisforum N5 MAX AI NAS 128 GB

Quality	Model	Quant	Memory	Speed	Runs
A+91Excellent quality (A+) · 91 of 100: how capable the model is at FP8, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	MMMiniMax H3 ImageMiniMax	FP8	72.0 GB	17 s	Runs well
A+92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking.	KKrea 2 TurboKrea	FP16	37.4 GB	8.3 s	Runs great
A+86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.	AGMing-Image 0.1 DesignAnt Group (inclusionAI)	FP16	63.9 GB	31 s	Runs well
A+92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.	IIdeogram 4Ideogram	FP16	57.3 GB	48 s	Slow
A84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	BFFLUX.2 [klein] 9BBlack Forest Labs	FP16	37.1 GB	3.5 s	Runs great
A+89Excellent quality (A+) · 89 of 100: how capable the model is at FP16, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	Qwen-Image 2.1 TurboAlibaba	FP16	46.7 GB	22 s	Runs well

Best Video models for the Minisforum N5 MAX AI NAS 128 GB

Quality	Model	Quant	Memory	Speed	Runs
A+86Excellent quality (A+) · 86 of 100: how capable the model is at FP8, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking.	LLTX-2.5 (22B, video + audio)Lightricks	FP8	48.3 GB	2.6 min	Runs great
A+88Excellent quality (A+) · 88 of 100: how capable the model is at FP8, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.	MMMiniMax H3 (33B, video + audio)MiniMax	FP8	66.8 GB	30.0 min	Slow
B68Good quality (B) · 68 of 100: how capable the model is at FP16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.	LLTX-Video 13B 0.9.8 (distilled)Lightricks	FP16	47.9 GB	1.9 min	Runs great
A+86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	Wan 2.2 I2V A14BAlibaba	FP16	58.0 GB	51.2 min	Very slow
A+86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	Wan 2.2 T2V A14BAlibaba	FP16	58.0 GB	51.2 min	Very slow

Best Decision models for the Minisforum N5 MAX AI NAS 128 GB

Quality	Model	Quant	Memory	Speed	Runs
A+90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3 Reranker 4BAlibaba	Q8_0	12.8 GB	89 ms	Runs great
A+88Excellent quality (A+) · 88 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking.	ZEzerank-2ZeroEntropy	Q8_0	12.8 GB	89 ms	Runs great
A+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.	JAJina Reranker v3.5Jina AI	F16	9.7 GB	22 ms	Runs great
A+86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking.	Shieldstral 1.0 3BMistral AI	Q8_0	12.6 GB	85 ms	Runs great
A84Great 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.	SAIntern-Decision 4BShanghai AI Lab	Q8_0	13.2 GB	69 ms	Runs great
A84Great 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.	JAJina Reranker v3Jina AI	F16	9.7 GB	22 ms	Runs great
A82Great 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.	LAd1 3BLiquid AI	F16	14.6 GB	75 ms	Runs great
A82Great 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.	Mmxbai-rerank-large v2Mixedbread	F16	11.4 GB	50 ms	Runs great