Can the AMD Instinct MI325X run DynaGuard 8B?

Yes, it runs well

Runs well. At Q6_K it needs about 20.4 GB of 256 GB usable and makes one decision in about 343 ms.

Best quant: Q6_K
Time per decision: 343 ms
Decisions per second: 2.9/s
Input assumed: 512 tokens
Returns: Reasoned verdict

Best app to run it on the AMD Instinct MI325X

On Linux

Inference server · runs on vLLM

The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.

vllm serve tomg-group-umd/DynaGuard-8B

Lemonade AMD’s own app: llama.cpp tuned for Radeon on Vulkan and ROCm.
LM Studio Point-and-click: search, download and chat in one window.

On Windows

Lemonade

Desktop app · runs on llama.cpp, ONNX Runtime GenAI (Ryzen AI NPU)

AMD’s own app: llama.cpp tuned for Radeon on Vulkan and ROCm.

lemonade pull mradermacher/DynaGuard-8B-GGUF:Q6_K

LM Studio Point-and-click: search, download and chat in one window.
llama.cpp Usually the first to support new model architectures.

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

Download DynaGuard 8B

Recommended for the AMD Instinct MI325X: Q6_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 Q6_K file (opens in a new tab)

huggingface.co/mradermacher/DynaGuard-8B-GGUF (opens in a new tab)

ollama run hf.co/mradermacher/DynaGuard-8B-GGUF:Q6_K

Original weights · Hugging Face

Full-precision files from University of Maryland, for fine-tuning, vLLM, Transformers.

huggingface.co/tomg-group-umd/DynaGuard-8B (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 78Great quality (A) · 78 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 78/100 (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: S 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Runs well: How well it runs on the AMD Instinct MI325X: 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.	35.2 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.	25.0 / 25
SpeedTime for one decision against a 100 ms target: reading the input plus any tokens the model writes.	8.1 / 15
ClarityHow easy the answer is to use in code: a probability or score earns the most, written feedback before a score the least.	10.0 / 15
Match score	78.3 / 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 Instinct MI325X

Quant	Memory needed	Available	Time per decision	Runs	Quality	Download
`Q4_K_M`	18.7 GB	256 GB	252 ms	Runs well	75Great quality (A) · 75 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q5_K_M`	19.5 GB	256 GB	295 ms	Runs well	76Great quality (A) · 76 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q6_K`	20.4 GB	256 GB	343 ms	Runs well	78Great quality (A) · 78 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`Q8_0`	22.4 GB	256 GB	451 ms	Slow	79Great quality (A) · 79 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab)
`F16`	30.1 GB	256 GB	926 ms	Slow	79Great quality (A) · 79 of 100: how capable the model is at F16, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking.	GGUF (opens in a new tab) Original weights (opens in a new tab)

Times are for one request with a 512-token input and about 160 tokens written. Batching servers process many requests at once.

Other hardware that runs it

75Great quality (A) · 75 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA B200 Q4_K_M · 174 ms · Runs well
78Great quality (A) · 78 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. AMD Instinct MI350X Q6_K · 277 ms · Runs well
78Great quality (A) · 78 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA H200 141GB SXM Q6_K · 368 ms · Runs well
78Great quality (A) · 78 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 H200 NVL Q6_K · 373 ms · Runs well
78Great quality (A) · 78 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 Instinct MI300X Q6_K · 383 ms · Runs well
76Great quality (A) · 76 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GH200 Grace Hopper (96 GB GPU) Q5_K_M · 371 ms · Runs well

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.