What AI models can the AMD Ryzen 9000 series (desktop) NAS (192 GB) run?

RAM: 192 GB
Usable for models: 173 GB
Memory bandwidth: 90 GB/s
Runs models on: CPU cores
Released: 2024

570 / 622 LLMs run Best: Qwen3.8 Flash Next (125B-A6B) 61 / 61 Image models run Best: MiniMax H3 Image 43 / 43 Video models run Best: MiniMax H3 (33B, video + audio) 70 / 70 Decision models run Best: OpenAI Privacy Filter

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 173 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	AMD
Type	NAS (network attached storage) processor
Share of memory for models	90% (what the NAS system and its storage services typically leave free at this size)
Chip	AMD Ryzen 9000 series (desktop)
AI accelerator	None. Models run on the processor cores.
NAS models with this chip	QNAP TS-h1277AFX
Memory type	System RAM, shared with the NAS operating system and its storage services
Bandwidth figure	89.6 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 AMD Ryzen 9000 series (desktop) NAS (192 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

1 product with the AMD Ryzen 9000 series (desktop) NAS (192 GB)

TS-h1277AFXQNAP · NAS · 32 or 192 GBProduct page (opens in a new tab)

Best LLMs for the AMD Ryzen 9000 series (desktop) NAS (192 GB)

Quality	Model	Quant	Memory	Speed	Runs
93Excellent quality (A+) · 93 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.	Qwen3.8 Flash Next (125B-A6B)Alibaba	`Q5_K_M`	142 GB	12.5 tok/s	Runs well
86Excellent quality (A+) · 86 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.	Kolibri 1 (78B-A3.5B)Aleph Alpha	`Q4_K_M`	62.2 GB	25.1 tok/s	Runs well
84Great quality (A) · 84 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	gpt-oss 120BOpenAI	`MXFP4`	81.3 GB	18.6 tok/s	Runs well
78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	MiniMax M2.7 (230B-A10B)MiniMax	`Q3_K_M`	129 GB	11.8 tok/s	Runs well
78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	Step 3.7 Flash (198B-A11B)StepFun	`Q3_K_M`	114 GB	10.7 tok/s	Runs well
77Great quality (A) · 77 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	MiniMax M2.5 (230B-A10B)MiniMax	`Q3_K_M`	129 GB	11.8 tok/s	Runs well
81Great quality (A) · 81 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.	Qwen3-Next 80B-A3B ThinkingAlibaba	`Q4_K_M`	64.2 GB	28.5 tok/s	Runs well
81Great quality (A) · 81 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.	Qwen3 Coder Next (80B-A3B)Alibaba	`Q4_K_M`	63.2 GB	28.5 tok/s	Runs well
86Excellent quality (A+) · 86 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.	Qwen3 235B-A22B Thinking 2507Alibaba	`Q4_K_M`	159 GB	4.2 tok/s	Slowtight fit
77Great quality (A) · 77 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.	Step 3.5 Flash (196B-A11B)StepFun	`Q3_K_M`	113 GB	10.7 tok/s	Runs well
76Great quality (A) · 76 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.	MiniMax M2.1 (230B-A10B)MiniMax	`Q3_K_M`	129 GB	11.8 tok/s	Runs well
88Excellent quality (A+) · 88 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.	Qwen3.6 35B-A3BAlibaba	`Q4_K_M`	36.5 GB	28.5 tok/s	Runs well

Best Image models for the AMD Ryzen 9000 series (desktop) NAS (192 GB)

Quality	Model	Quant	Memory	Speed	Runs
93Excellent quality (A+) · 93 of 100: how capable the model is at FP16, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.	MiniMax H3 ImageMiniMax	`FP16`	138 GB	8.1 min	Very slow
92Excellent quality (A+) · 92 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.	FLUX.2 [dev]Black Forest Labs	`FP16`	116 GB	29.2 min	Very slow
92Excellent quality (A+) · 92 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.	Cosmos3-Super Text2Image (64B)NVIDIA	`FP16`	133 GB	32.4 min	Very slow
88Excellent quality (A+) · 88 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.	HunyuanImage 3.0 (80B-A13B)Tencent	`FP8`	86.9 GB	43.7 min	Very slow
92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.	Ideogram 4Ideogram	`FP16`	57.3 GB	20.2 min	Very slow
93Excellent quality (A+) · 93 of 100: how capable the model is at FP16, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.	Qwen-Image 2.1Alibaba	`FP16`	57.0 GB	48.6 min	Very slow

Best Video models for the AMD Ryzen 9000 series (desktop) NAS (192 GB)

Quality	Model	Quant	Memory	Speed	Runs
90Excellent quality (A+) · 90 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.	MiniMax H3 (33B, video + audio)MiniMax	`FP16`	113 GB	14.0 h	Very slow
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	30.4 h	Very slow
88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.	LTX-2.5 (22B, video + audio)Lightricks	`FP16`	82.5 GB	73.7 min	Very slow
88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking.	Kandinsky 6.0 Pro (29B, video + audio)Sber AI	`FP16`	85.4 GB	39.7 h	Very slow
86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.	LTX-2.3Lightricks	`FP16`	75.4 GB	5.4 h	Very slow

Best Decision models for the AMD Ryzen 9000 series (desktop) NAS (192 GB)

Quality	Model	Quant	Memory	Speed	Runs
78Great 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.	OpenAI Privacy FilterOpenAI	`F16`	3.8 GB	36 ms	Runs great
68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	Llama Prompt Guard 2 22MMeta	`F16`	0.8 GB	96 ms	Runs great
80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.	GLiNER2.5 DecideFastino	`Q8_0`	1.2 GB	279 ms	Runs well
86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.	Jina Reranker v3.5Jina AI	`Q8_0`	15.3 GB	636 ms	Slow
66Good quality (B) · 66 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.	GLiClass Base v3Knowledgator	`Q8_0`	0.8 GB	111 ms	Runs great
84Great quality (A) · 84 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.	Jina Reranker v3Jina AI	`Q8_0`	15.3 GB	636 ms	Slow
64Good quality (B) · 64 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.	DeBERTa v3 Base Zero-shot v2.0Moritz Laurer	`Q8_0`	0.8 GB	105 ms	Runs great
74Great quality (A) · 74 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.	GLiClass ModernBERT Large v3Knowledgator	`Q8_0`	1.1 GB	228 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.