Phi-4 Reasoning Vision 15B on AMD Ryzen AI 9 HX PRO 370 / 375 NAS (48 GB)

Can the AMD Ryzen AI 9 HX PRO 370 / 375 NAS (48 GB) run Phi-4 Reasoning Vision 15B?

Yes, it runs well

Runs well. At Q2_K it needs about 11.2 GB of 36.0 GB usable, with an estimated speed of 12.4 tok/s.

Best quant: Q2_K
Generation speed: 12.4 tok/s
Prompt processing: 1,181 tok/s
First token (1K prompt): 0.9 s
Largest safe context: 32K

Download Phi-4 Reasoning Vision 15B

Original weights · Hugging Face

Full-precision files from Microsoft, for fine-tuning, vLLM, Transformers.

huggingface.co/microsoft/Phi-4-reasoning-vision-15B (opens in a new tab)

No sign-in needed.

Links checked 3 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q2_K, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Runs well: How well it runs on the AMD Ryzen AI 9 HX PRO 370 / 375 NAS (48 GB): speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	22.1 / 45
Memory fitFull marks when the model fits in the share of the NAS’s memory that models can use (the rest stays with the NAS system and its storage services); fewer when it goes past that limit.	25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	8.4 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	7.2 / 15
Match score	62.6 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every quantization on the AMD Ryzen AI 9 HX PRO 370 / 375 NAS (48 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q2_K`	11.2 GB	36.0 GB	12.4 tok/s	Runs well	49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q3_K_M`	12.6 GB	36.0 GB	9.8 tok/s	Slow	58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q4_K_M`	14.4 GB	36.0 GB	7.6 tok/s	Slow	66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q5_K_M`	15.9 GB	36.0 GB	6.3 tok/s	Slow	67Good quality (B) · 67 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q6_K`	17.6 GB	36.0 GB	5.3 tok/s	Slow	69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q8_0`	21.2 GB	36.0 GB	3.9 tok/s	Slow	70Great quality (A) · 70 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`F16`	35.4 GB	36.0 GB	1.8 tok/s	Very slowtight fit	70Great quality (A) · 70 of 100: how capable the model is at F16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)

Memory figures assume 8K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

70Great quality (A) · 70 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 Q8_0 · 41.7 tok/s · Runs great
70Great quality (A) · 70 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3090 Q8_0 · 38.7 tok/s · Runs great
69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX Q6_K · 46.6 tok/s · Runs great
70Great quality (A) · 70 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q8_0 · 74.1 tok/s · Runs great
69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPER Q6_K · 41.5 tok/s · Runs well (tight fit)
69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5070 Ti Q6_K · 50.5 tok/s · Runs well (tight fit)

Quick answers

How much memory does Phi-4 Reasoning Vision 15B need on the AMD Ryzen AI 9 HX PRO 370 / 375 NAS 48GB?

At Q2_K it needs about 11.2 GB. The AMD Ryzen AI 9 HX PRO 370 / 375 NAS 48GB has 36.0 GB usable.

How fast is Phi-4 Reasoning Vision 15B on the AMD Ryzen AI 9 HX PRO 370 / 375 NAS 48GB?

About 12.4 tok/s at Q2_K, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Phi-4 Reasoning Vision 15B should I use on the AMD Ryzen AI 9 HX PRO 370 / 375 NAS 48GB?

Q2_K. Of the versions that fit, it is the one that runs best; when two run equally well, the check prefers the higher-rated one.

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.