Minisforum AI NAS N5 AIR-7640

Configurations

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

Specifications 16.0 GB configuration

Maker	MMinisforum
Type	NAS
Processor	AMD Ryzen 5 7640HS NAS (16 GB)
Memory (RAM)	16.0 GB
Usable for AI models	12.0 GB
Memory bandwidth	90 GB/s
FP16 compute	0.6 TFLOPS
Runs models on	CPU cores
Drive bays	5x 3.5/2.5in SATA (30TB each, 150TB) + 3x M.2 NVMe
NAS system	MinisCloud OS
Containers (Docker)	Yes
Virtual machines	Yes
Memory upgrade	DDR5 SO-DIMM, 4800 or 5600 MT/s (non-ECC; AMD lists ECC 'No' for this… · 2 slots · up to 96.0 GB per the maker · non-ECC
Graphics card options	PCIe: 1x internal PCIe x16 slot, PCIe 4.0 x4 electrical. External GPU: 1x OCuLink port (rear); 2x USB4.
Notes	AMD Ryzen 5 7640HS. 6-core Zen 4 with Radeon 760M and up to 96GB dual-channel DDR5, Docker or a replacement OS. Small models at CPU speeds; add a GPU through the PCIe slot or OCuLink for more.
Product page	store.minisforum.com (opens in a new tab)

Running AI on the Minisforum AI NAS N5 AIR-7640

It can, with limits: expect small models only, at modest speed. Models run on its CPU cores, and this configuration leaves about 12.0 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 AI NAS N5 AIR-7640 16.0 GB

Quality	Model	Quant	Memory	Speed	Runs
B66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.	JBMellum2.1 Thinking (12B-A2.5B)JetBrains	Q4_K_M	9.1 GB	26.7 tok/s	Runs well
B58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.	DGMaple Preview (20B-A1B)DeepGrove	Q3_K_M	11.6 GB	52.7 tok/s	Runs welltight fit
B58Good quality (B) · 58 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.	AGLing 3.0 Tiny (8B-A1.3B)Ant Group (inclusionAI)	Q5_K_M	7.4 GB	40.1 tok/s	Runs great
C51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.	LALFM2.5 24B-A2BLiquid AI	Q2_K	11.3 GB	42.6 tok/s	Runs welltight fit
B66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.	Nemotron 3.5 Bolt E4BNVIDIA	Q4_K_M	6.6 GB	16.3 tok/s	Runs well
B67Good quality (B) · 67 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.	IOK2 Horizon 7BInstitute of Foundation Models	Q3_K_M	7.2 GB	10.5 tok/s	Runs well
B64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.	Gemma 4 E4BGoogle	Q4_K_M	6.6 GB	16.3 tok/s	Runs well
C49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.	AGLing Mini 2.0 (16B-A1.4B)Ant Group (inclusionAI)	Q4_K_M	11.8 GB	44.5 tok/s	Runs welltight fit
B57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.	MAKimi-VL A3B Thinking 2506Moonshot AI	Q4_K_M	11.8 GB	22.6 tok/s	Runs welltight fit
C49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.	LALFM2.5 8B-A1BLiquid AI	Q4_K_M	6.8 GB	42.0 tok/s	Runs great

Best Image models for the Minisforum AI NAS N5 AIR-7640 16.0 GB

Quality	Model	Quant	Memory	Speed	Runs
A76Great quality (A) · 76 of 100: how capable the model is at FP8, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.	BFFLUX.2 [klein] 4BBlack Forest Labs	FP8	10.2 GB	58 s	Slow
A84Great quality (A) · 84 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.	BFFLUX 3 Image KleinBlack Forest Labs	Q4 GGUF	10.2 GB	7.3 min	Very slow
A78Great quality (A) · 78 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.	Z-Image TurboAlibaba (Tongyi)	Q4 GGUF	10.1 GB	3.2 min	Very slow
A79Great quality (A) · 79 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.	BERNIE-Image TurboBaidu	Q4 GGUF	11.3 GB	4.1 min	Very slowtight fit
A76Great quality (A) · 76 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.	Z-ImageAlibaba (Tongyi)	Q4 GGUF	10.1 GB	21.9 min	Very slow
A78Great quality (A) · 78 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.	BFFLUX.2 [klein] 9BBlack Forest Labs	Q4 GGUF	8.0 GB	2.4 min	Very slowencoder unloaded after use

Best Video models for the Minisforum AI NAS N5 AIR-7640 16.0 GB

Quality	Model	Quant	Memory	Speed	Runs
C49Fair quality (C) · 49 of 100: how capable the model is at FP8, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking.	LLTX-Video 2BLightricks	FP8	10.8 GB	24.1 min	Slowtight fit
A83Great quality (A) · 83 of 100: how capable the model is at FP8, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking.	BDBernini-R A14B (video generation + editing)ByteDance	FP8	10.7 GB	15.1 h	Very slowtight fit · CPU offload
A74Great quality (A) · 74 of 100: how capable the model is at FP8, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.	THY-OmniWeaving (8.3B, unified video)Tencent	FP8	7.8 GB	11.1 h	Very slowCPU offload
B55Good quality (B) · 55 of 100: how capable the model is at FP16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.	Wan 2.1 T2V 1.3BAlibaba	FP16	8.4 GB	4.5 h	Very slowencoder unloaded after use
B55Good quality (B) · 55 of 100: how capable the model is at FP16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking.	Wan 2.1 VACE 1.3BAlibaba	FP16	10.1 GB	4.9 h	Very slowencoder unloaded after use

Best Decision models for the Minisforum AI NAS N5 AIR-7640 16.0 GB

Quality	Model	Quant	Memory	Speed	Runs
A78Great quality (A) · 78 of 100: how capable the model is at F16, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking.	OAOpenAI Privacy FilterOpenAI	F16	3.8 GB	65 ms	Runs great
A+86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	JAJina Reranker v3.5Jina AI	Q8_0	2.4 GB	1.2 s	Slow
B68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.	Llama Prompt Guard 2 22MMeta	Q8_0	0.7 GB	154 ms	Runs well
A80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.	FGLiNER2.5 DecideFastino	Q8_0	1.2 GB	520 ms	Slow
A+90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.	Qwen3 Reranker 4BAlibaba	Q8_0	6.1 GB	7.9 s	Very slow
A84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.	JAJina Reranker v3Jina AI	Q8_0	2.4 GB	1.2 s	Slow
A+88Excellent quality (A+) · 88 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	ZEzerank-2ZeroEntropy	Q8_0	6.1 GB	7.9 s	Very slow
A+89Excellent quality (A+) · 89 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 Reranker 8BAlibaba	Q6_K	8.6 GB	16.0 s	Very slow