Nemotron 3 Ultra 550B-A55B on AMD Instinct MI325X

Can the AMD Instinct MI325X run Nemotron 3 Ultra 550B-A55B?

Yes, it runs well (tight fit)

Runs well (tight fit). At Q2_K it needs about 238 GB of 256 GB usable, with an estimated speed of 119 tok/s.

Best quant: Q2_K
Generation speed: 119 tok/s
Prompt processing: 1,842 tok/s
First token (1K prompt): 0.6 s
Largest safe context: 256K

Best app to run it on the AMD Instinct MI325X

On Linux

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 unsloth/NVIDIA-Nemotron-3-Ultra-550B-A55B-GGUF:UD-Q2_K_XL

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

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 unsloth/NVIDIA-Nemotron-3-Ultra-550B-A55B-GGUF:UD-Q2_K_XL

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

Want an agent? Nemotron 3 Ultra 550B-A55B 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, 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 Nemotron 3 Ultra 550B-A55B

Recommended for the AMD Instinct MI325X: Q2_K. Every other quantization has its own download link in the table below.

Ollama

Ollama offers this only as a cloud model (it runs on Ollama’s servers, not your machine). To run it locally, use the GGUF files below.

Quantized files · GGUF

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

Download the Q2_K (UD-Q2_K_XL) files (opens in a new tab)

huggingface.co/unsloth/NVIDIA-Nemotron-3-Ultra-550B-A55B-GGUF (opens in a new tab)

ollama run hf.co/unsloth/NVIDIA-Nemotron-3-Ultra-550B-A55B-GGUF

Original weights · Hugging Face

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

huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 (opens in a new tab)

No sign-in needed.

Official repo · GitHub

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

github.com/NVIDIA-NeMo/Nemotron (opens in a new tab)

NVIDIA’s Nemotron repo with recipes for the whole family.

git clone https://github.com/NVIDIA-NeMo/Nemotron

Links checked 1 day 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 83/100 (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 welltight fit: 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.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.	29.4 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.	24.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.	15.0 / 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	83.4 / 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	Speed	Runs	Quality	Download
`Q2_K`	238 GB	256 GB	119 tok/s	Runs welltight 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.	GGUF (UD-Q2_K_XL) · folder (opens in a new tab)
`Q3_K_M`	288 GB	256 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`	355 GB	256 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`	411 GB	256 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`	473 GB	256 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`	608 GB	256 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`	1,135 GB	256 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.	GGUF · folder (opens in a new tab) 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

88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. Apple M3 Ultra (512 GB) Q4_K_M · 14.9 tok/s · Runs well (tight fit)
88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Apple M5 Ultra (512 GB) Q4_K_M · 21.4 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 84/100 (quality, fit, speed and memory use) sets the ranking. AMD Instinct MI350X Q2_K · 141 tok/s · Runs great
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 GB300 Grace Blackwell Ultra Desktop Superchip Q2_K · 144 tok/s · Runs well (tight fit)
78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. AMD EPYC 7002 / 7003 series NAS (512 GB) Q3_K_M · 3.2 tok/s · Slow
88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. Intel Xeon Silver (4100 to 4300 series) NAS (512 GB) Q4_K_M · 1.2 tok/s · Very slow

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.