Llama Guard 4 12B on AMD Ryzen AI 9 HX PRO 370 / 375 NAS (96 GB)

Can the AMD Ryzen AI 9 HX PRO 370 / 375 NAS (96 GB) run Llama Guard 4 12B?

Yes, but slowly

Slow. At Q6_K it needs about 16.6 GB of 72.0 GB usable and makes one decision in about 1.3 s.

Best quant: Q6_K
Time per decision: 1.3 s
Decisions per second: 0.8/s
Input assumed: 512 tokens
Returns: Fixed labels

Download Llama Guard 4 12B

Original weights · Hugging Face

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

huggingface.co/meta-llama/Llama-Guard-4-12B (opens in a new tab)

Free Hugging Face account needed: request access on the model page, and Meta approves it (usually within minutes to a few hours).

Links checked 4 hours ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q6_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 Slow: How well it runs on the AMD Ryzen AI 9 HX PRO 370 / 375 NAS (96 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.

PrecisionEditorial precision tier from the model’s published benchmarks, scaled by the quantization or precision used.	29.4 / 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
SpeedTime for one decision against a 100 ms target: reading the input plus any tokens the model writes.	4.2 / 15
ClarityHow easy the answer is to use in code: a probability or score earns the most, written feedback before a score the least.	12.0 / 15
Match score	70.6 / 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 (96 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`Q4_K_M`	14.1 GB	72.0 GB	977 ms	Slow	62Good quality (B) · 62 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`	15.3 GB	72.0 GB	1.1 s	Slow	64Good quality (B) · 64 of 100: how capable the model is at Q5_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)
`Q6_K`	16.6 GB	72.0 GB	1.3 s	Slow	65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`Q8_0`	19.5 GB	72.0 GB	1.6 s	Very slow	66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.	All files (opens in a new tab)
`F16`	30.8 GB	72.0 GB	3.0 s	Very slow	66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)

Times are for one request with a 512-token input and about 6 tokens written. Batching servers process many requests at once.

Other hardware that runs it

65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Q6_K · 119 ms · Runs great
65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5090 Q6_K · 133 ms · Runs great
65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX Q6_K · 187 ms · Runs well
65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 Q6_K · 191 ms · Runs well
65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5080 Q6_K · 244 ms · Runs well
65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 9070 XT Q6_K · 259 ms · Runs well

Quick answers

How much memory does Llama Guard 4 12B need on the AMD Ryzen AI 9 HX PRO 370 / 375 NAS 96GB?

At Q6_K it needs about 16.6 GB. The AMD Ryzen AI 9 HX PRO 370 / 375 NAS 96GB has 72.0 GB usable.

How fast is Llama Guard 4 12B on the AMD Ryzen AI 9 HX PRO 370 / 375 NAS 96GB?

It makes one decision in about 1.3 s at Q6_K, an estimate from the hardware and the size of the model.

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.