Can Nemotron Cascade 2 30B A3B run on AMD Instinct MI250X 128GB?

YES — Runs Great

S85Excellent

○Estimated from fit model

Nemotron Cascade 2 30B A3B needs ~34.9 GB VRAM. AMD Instinct MI250X 128GB has 128.0 GB. With Q4_K_M quantization, expect ~386 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: HighStack: StandardBottleneck: Balanced

Operating mode

Choose the run profile you care about

Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.

Current mode

Balanced

Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 34.9 GB, 385.8 tok/s, Runs well

34.9 GB required128.0 GB available

27% VRAM used

Fit status

Runs well

Decode

385.8 tok/s

TTFT

502 ms

Safe context

262K

Memory

34.9 GB / 128.0 GB

Memory breakdown

Weights18.3 GB

KV Cache2.9 GB

Runtime0.9 GB

Headroom12.8 GB

See how fast it feels

See how fast it feelsNemotron Cascade 2 30B A3B on AMD Instinct MI250X 128GB
1st promptCold start — includes initialization
>Write a Python function to sort a list
Here's a Python function that sorts a list using quicksort:

def quicksort(arr):
 if len(arr) <= 1:
 return arr
 pivot = arr[len(arr) // 2]
 left = [x for x in arr if x < pivot]
 middle = [x for x in arr if x == pivot]
 right = [x for x in arr if x > pivot]
 return quicksort(left) + middle + quicksort(right)

# Example usage
numbers = [3, 6, 8, 10, 1, 2, 1]
print(quicksort(numbers)) # [1, 1, 2, 3, 6, 8, 10]

The algorithm picks a pivot, partitions the list into smaller, equal, and larger elements, then recursively sorts each partition and concatenates the results.
2nd promptWarm — model ready, no init overhead
>Now add type hints and a docstring
def quicksort(arr: list[int]) -> list[int]:
 """Sort a list using the quicksort algorithm.

 Args:
 arr: List of integers to sort.

 Returns:
 A new sorted list.
 """
 if len(arr) <= 1:
 return arr
 pivot = arr[len(arr) // 2]
 left = [x for x in arr if x < pivot]
 middle = [x for x in arr if x == pivot]
 right = [x for x in arr if x > pivot]
 return quicksort(left) + middle + quicksort(right)

Added type hints for the input and return type, plus a Google-style docstring.
Estimated: 385.8 tok/s decode · 502ms TTFT (warm) · 965 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

No major red flags

This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.

Best improvement path

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	S	Runs well	385.8 tok/s	350 ms	262K
Coding	S	Runs well	385.8 tok/s	502 ms	262K
Agentic Coding	S	Runs well	385.8 tok/s	730 ms	262K
Reasoning	S	Runs well	385.8 tok/s	593 ms	262K
RAG	S	Runs well	385.8 tok/s	912 ms	262K

Quantization options

How Nemotron Cascade 2 30B A3B (30B params) fits at each quantization level on AMD Instinct MI250X 128GB (128.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	11.7 GB	Low	A76
Q3_K_S	3	14.7 GB	Low	A76
NVFP4	4	16.8 GB	Medium	A77
Q4_K_M	4	18.3 GB	Medium	A77
Q5_K_M	5	21.6 GB	High	A77
Q6_K	6	24.6 GB	High	A77
Q8_0	8	32.1 GB	Very High	A79
F16Best for your GPU	16	61.5 GB	Maximum	A83

Get started

Copy-paste commands to run Nemotron Cascade 2 30B A3B on your machine.

Run

ollama run nemotron-cascade-2

Your hardware

More models your AMD Instinct MI250X 128GB can run

Model	Params	Grade	Decode
👁 Mistral Devstral 2 123B Instruct	123B	S	36.2 tok/s
👁 Alibaba Qwen3-Coder 30B A3B Instruct	30.5B	S	377.4 tok/s
👁 Alibaba Qwen 3.5 122B A10B	122B	S	100.3 tok/s
👁 Alibaba Qwen 3.6 35B A3B	35B	S	317.2 tok/s
👁 Alibaba Qwen 3.5 35B A3B	35B	S	344.9 tok/s

Frequently asked questions

See all results for AMD Instinct MI250X 128GB See all hardware for Nemotron Cascade 2 30B A3B

URL: https://willitrunai.com/can-run/nemotron-cascade-2-30b-a3b-on-instinct-mi250x-128gb

⇱ Nemotron Cascade 2 30B A3B on AMD Instinct MI250X 128GB? YES