StableLM 2 12B Chat 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 StableLM 2 12B Chat?

Yes, it runs well

Runs well. At Q3_K_M it needs about 13.1 GB of 72.0 GB usable, with an estimated speed of 12.2 tok/s.

Best quant: Q3_K_M
Generation speed: 12.2 tok/s
Prompt processing: 1,470 tok/s
First token (1K prompt): 0.7 s
Largest safe context: 4K

Best app to run it on the AMD Ryzen AI 9 HX PRO 370 / 375 NAS (96 GB)

On Linux

Ollama

Command line + local API · runs on llama.cpp (ggml), MLX (Apple silicon, preview)

One command with Ollama’s own build of this model.
Serves an OpenAI-compatible API that other apps and coding tools can use.

ollama run stablelm2:12b-chat-q3_K_M

llama.cpp Usually the first to support new model architectures.
KoboldCpp

How we choose: the files published for this model, which apps run in a container on a NAS without a graphics card (models run on its processor), and whether the model fits fully in the memory models can use. Details.

Download StableLM 2 12B Chat

Recommended for the AMD Ryzen AI 9 HX PRO 370 / 375 NAS (96 GB): Q3_K_M. Every other quantization has its own download link in the table below.

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

ollama run stablelm2:12b-chat-q3_K_M

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

Download the Q3_K_M file (opens in a new tab)

huggingface.co/stabilityai/stablelm-2-12b-chat-GGUF (opens in a new tab)

ollama run hf.co/stabilityai/stablelm-2-12b-chat-GGUF:Q3_K_M

Original weights · Hugging Face

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

huggingface.co/stabilityai/stablelm-2-12b-chat (opens in a new tab)

No sign-in needed.

Links checked 2 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 23Basic quality (D) · 23 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking.: How capable the model itself is at Q3_K_M, 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 (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.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	10.6 / 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.	8.3 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	4.2 / 15
Match score	48.1 / 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
`Q2_K`	12.1 GB	72.0 GB	15.5 tok/s	Runs well	19Basic quality (D) · 19 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q3_K_M`	13.1 GB	72.0 GB	12.2 tok/s	Runs well	23Basic quality (D) · 23 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q4_K_M`	14.6 GB	72.0 GB	9.4 tok/s	Slow	26Basic quality (D) · 26 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	15.8 GB	72.0 GB	7.8 tok/s	Slow	27Basic quality (D) · 27 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	17.2 GB	72.0 GB	6.5 tok/s	Slow	27Basic quality (D) · 27 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	20.1 GB	72.0 GB	4.8 tok/s	Slow	28Basic quality (D) · 28 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	31.5 GB	72.0 GB	2.2 tok/s	Very slow	28Basic quality (D) · 28 of 100: how capable the model is at F16, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab) Original weights (opens in a new tab)

Memory figures assume 4K of context. Longer conversations or documents grow the KV cache.

Other hardware that runs it

28Basic quality (D) · 28 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. AMD Radeon RX 7900 XTX Q8_0 · 42.6 tok/s · Runs great
28Basic quality (D) · 28 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 3090 Q8_0 · 48.2 tok/s · Runs great
28Basic quality (D) · 28 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4090 Q8_0 · 51.9 tok/s · Runs great
27Basic quality (D) · 27 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4070 Ti SUPER Q6_K · 47.1 tok/s · Runs great
27Basic quality (D) · 27 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 4080 SUPER Q6_K · 51.6 tok/s · Runs great
27Basic quality (D) · 27 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GeForce RTX 5070 Ti Q6_K · 62.9 tok/s · Runs great

Quick answers

How much memory does StableLM 2 12B Chat need on the AMD Ryzen AI 9 HX PRO 370 / 375 NAS 96GB?

At Q3_K_M it needs about 13.1 GB. The AMD Ryzen AI 9 HX PRO 370 / 375 NAS 96GB has 72.0 GB usable.

How fast is StableLM 2 12B Chat on the AMD Ryzen AI 9 HX PRO 370 / 375 NAS 96GB?

About 12.2 tok/s at Q3_K_M, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of StableLM 2 12B Chat should I use on the AMD Ryzen AI 9 HX PRO 370 / 375 NAS 96GB?

Q3_K_M. 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.