Step 3.7 Flash (198B-A11B) 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 Step 3.7 Flash (198B-A11B)?

Yes, but slowly (far over GPU memory limit)

Slow (far over GPU memory limit). At Q2_K it needs about 87.3 GB of 72.0 GB usable, with an estimated speed of 13.8 tok/s.

Best quant: Q2_K
Generation speed: 13.8 tok/s
Prompt processing: 1,623 tok/s
First token (1K prompt): 0.6 s
Largest safe context: —

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

On Linux

llama.cpp

Command line + local API · runs on llama.cpp

Splits the model between GPU memory and system RAM, which this setup needs.
Gives you direct control of how many layers sit on the GPU, the best way to squeeze a model that doesn’t quite fit.
Usually the first to support new model architectures.

llama-server -hf bartowski/Step-3.7-Flash-GGUF:Q2_K

Ollama Splits the model between GPU memory and system RAM, which this setup needs.
KoboldCpp Splits the model between GPU memory and system RAM, which this setup needs.

Want an agent? Step 3.7 Flash (198B-A11B) supports tool use, so you can pair a llama.cpp or MLX LM server with one of these. Apps that run on this computer come first.

Coding agents

Personal assistants

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 Step 3.7 Flash (198B-A11B)

Recommended for the AMD Ryzen AI 9 HX PRO 370 / 375 NAS (96 GB): Q2_K. Every other quantization has its own download link in the table below.

Quantized files · GGUF

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

Download the Q2_K files (opens in a new tab)

huggingface.co/bartowski/Step-3.7-Flash-GGUF (opens in a new tab)

ollama run hf.co/bartowski/Step-3.7-Flash-GGUF

Original weights · Hugging Face

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

huggingface.co/stepfun-ai/Step-3.7-Flash (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from StepFun. The weights themselves download from Hugging Face.

github.com/stepfun-ai/Step-3.7-Flash (opens in a new tab)

git clone https://github.com/stepfun-ai/Step-3.7-Flash

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

How it’s rated

Quality 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 57/100 (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 Slowfar over GPU memory limit: 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.	29.5 / 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.	4.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	8.8 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.	15.0 / 15
Match score	57.3 / 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`	87.3 GB	72.0 GB	13.8 tok/s	Slowfar over GPU memory limit	65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q3_K_M`	105 GB	72.0 GB	—	Won't run	78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q4_K_M`	130 GB	72.0 GB	—	Won't run	88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q5_K_M`	150 GB	72.0 GB	—	Won't run	90Excellent quality (A+) · 90 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 12/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q6_K`	172 GB	72.0 GB	—	Won't run	92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 12/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`Q8_0`	220 GB	72.0 GB	—	Won't run	93Excellent quality (A+) · 93 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 12/100 (quality, fit, speed and memory use) sets the ranking.	GGUF · folder (opens in a new tab)
`F16`	410 GB	72.0 GB	—	Won't run	93Excellent quality (A+) · 93 of 100: how capable the model is at F16, whatever it runs on. Match score 12/100 (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

90Excellent quality (A+) · 90 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. Apple M3 Ultra (256 GB) Q5_K_M · 53.0 tok/s · Runs great
88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Apple M2 Ultra (192 GB) Q4_K_M · 61.1 tok/s · Runs well (tight fit)
92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. Apple M3 Ultra (512 GB) Q6_K · 45.6 tok/s · Runs great
78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GB10 (128 GB) Q3_K_M · 34.9 tok/s · Runs well (tight fit)
65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. Apple M4 Max (128 GB) Q2_K · 67.9 tok/s · Runs well (tight fit)
65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Q2_K · 162 tok/s · Runs well (tight fit)

Quick answers

How much memory does Step 3.7 Flash (198B-A11B) need on the AMD Ryzen AI 9 HX PRO 370 / 375 NAS 96GB?

At Q2_K it needs about 87.3 GB. The AMD Ryzen AI 9 HX PRO 370 / 375 NAS 96GB has 72.0 GB usable.

How fast is Step 3.7 Flash (198B-A11B) on the AMD Ryzen AI 9 HX PRO 370 / 375 NAS 96GB?

About 13.8 tok/s at Q2_K, an estimate from the hardware’s memory bandwidth and the size of the model.

Which quantization of Step 3.7 Flash (198B-A11B) should I use on the AMD Ryzen AI 9 HX PRO 370 / 375 NAS 96GB?

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.