Minisforum AI Agent NAS N5 MAX-P495

Specifications

Maker	MMinisforum
Type	NAS
Processor	AMD Ryzen AI Max+ PRO 495 NAS (192 GB)
Memory (RAM)	192 GB
Usable for AI models	159 GB
Memory bandwidth	273 GB/s
FP16 compute	61.4 TFLOPS
Runs models on	GPU (Vulkan)
Drive bays	Up to 200TB local storage (bay layout not stated)
Memory upgrade	Unified memory at 8533 MT/s (type and whether soldered not stated) · up to 192 GB per the maker
Availability	Announced, not on general sale when checked
Notes	AMD Ryzen AI MAX+ PRO 495. Announced with up to 192GB memory, of which the maker says up to 160GB can serve as graphics memory, aimed at local models and agents. Not on sale yet, so nothing is verified. Announced or in crowdfunding; not on general sale when checked (November 2026).
Product page	www.minisforum.com (opens in a new tab)

Running AI on the Minisforum AI Agent NAS N5 MAX-P495

Yes, it runs AI models on the NAS itself. Models run on its GPU (Vulkan), and this configuration leaves about 159 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.

AI features from Minisforum

Best LLMs for the Minisforum AI Agent NAS N5 MAX-P495

Quality	Model	Quant	Memory	Speed	Runs
A+91Excellent quality (A+) · 91 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3.8 Flash Next (125B-A6B)Alibaba	Q4_K_M	123 GB	41.4 tok/s	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.	Qwen3-Next 80B-A3B ThinkingAlibaba	Q8_0	99.7 GB	41.3 tok/s	Runs great
A+86Excellent quality (A+) · 86 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 Coder Next (80B-A3B)Alibaba	Q8_0	98.0 GB	41.3 tok/s	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.	Qwen3 Next 80B-A3B InstructAlibaba	Q8_0	99.7 GB	41.3 tok/s	Runs great
A+90Excellent quality (A+) · 90 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	AAKolibri 1 (78B-A3.5B)Aleph Alpha	Q6_K	77.6 GB	47.9 tok/s	Runs great
A+88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	MMMiniMax M2.7 (230B-A10B)MiniMax	Q4_K_M	155 GB	26.3 tok/s	Runs welltight fit
A+87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking.	SFStep 3.5 Flash (196B-A11B)StepFun	Q4_K_M	135 GB	24.1 tok/s	Runs well
A79Great quality (A) · 79 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking.	AGLing 3.0 Flash (127B-A5B)Ant Group (inclusionAI)	Q5_K_M	104 GB	40.2 tok/s	Runs great
A+87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking.	MMMiniMax M2.5 (230B-A10B)MiniMax	Q4_K_M	155 GB	26.3 tok/s	Runs welltight fit
A+88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking.	SFStep 3.7 Flash (198B-A11B)StepFun	Q4_K_M	137 GB	24.1 tok/s	Runs welltight fit

Best Image models for the Minisforum AI Agent NAS N5 MAX-P495

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 87/100 (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 87/100 (quality, fit, speed and memory use) sets the ranking.	BFFLUX.2 [dev]Black Forest Labs	FP16	116 GB	67 s	Slow
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.	KKrea 2 TurboKrea	FP16	37.4 GB	8.1 s	Runs great
A+92Excellent quality (A+) · 92 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.	Cosmos3-Super Text2Image (64B)NVIDIA	FP16	133 GB	75 s	Slow
A+91Excellent quality (A+) · 91 of 100: how capable the model is at FP16, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	BFFLUX 3 Image KleinBlack Forest Labs	FP16	22.4 GB	11 s	Runs great
A84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	BFFLUX.2 [klein] 9BBlack Forest Labs	FP16	37.1 GB	3.4 s	Runs great

Best Video models for the Minisforum AI Agent NAS N5 MAX-P495

Quality	Model	Quant	Memory	Speed	Runs
A+88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	LLTX-2.5 (22B, video + audio)Lightricks	FP16	82.5 GB	2.8 min	Runs great
A+90Excellent quality (A+) · 90 of 100: how capable the model is at FP16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	MMMiniMax H3 (33B, video + audio)MiniMax	FP16	113 GB	32.5 min	Slow
A+88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.	Cosmos3-Super Image2Video (64B)NVIDIA	FP16	139 GB	70.3 min	Very slowtight fit
A+88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.	SAKandinsky 6.0 Pro (29B, video + audio)Sber AI	FP16	85.4 GB	1.5 h	Very slow
B68Good quality (B) · 68 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.	LLTX-Video 13B 0.9.8 (distilled)Lightricks	FP16	47.9 GB	1.9 min	Runs great

Best Decision models for the Minisforum AI Agent NAS N5 MAX-P495

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	17.9 GB	85 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	17.9 GB	85 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	14.8 GB	21 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	17.6 GB	82 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	18.2 GB	65 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	14.8 GB	21 ms	Runs great
A+89Excellent quality (A+) · 89 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 Reranker 8BAlibaba	Q6_K	20.4 GB	155 ms	Runs well
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	19.6 GB	71 ms	Runs great