Can Nemotron Cascade 2 30B A3B run on AMD Instinct MI210 64GB?

YES — Runs Great

S89Excellent

Estimated from fit model

Nemotron Cascade 2 30B A3B needs ~28.5 GB VRAM. AMD Instinct MI210 64GB has 64.0 GB. With Q4_K_M quantization, expect ~172 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) — 28.5 GB, 172.2 tok/s, Runs well

28.5 GB required64.0 GB available

45% VRAM used

Fit status

Runs well

Decode

172.2 tok/s

TTFT

1124 ms

Safe context

210K

Memory

28.5 GB / 64.0 GB

Memory breakdown

Weights18.3 GB

KV Cache2.9 GB

Runtime0.9 GB

Headroom6.4 GB

See how fast it feels

See how fast it feelsNemotron Cascade 2 30B A3B on AMD Instinct MI210 64GB
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: 172.2 tok/s decode · 1.1s TTFT (warm) · 431 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	172.2 tok/s	613 ms	210K
Coding	S	Runs well	172.2 tok/s	1124 ms	210K
Agentic Coding	S	Runs well	172.2 tok/s	1635 ms	210K
Reasoning	S	Runs well	172.2 tok/s	1329 ms	210K
RAG	S	Runs well	172.2 tok/s	2044 ms	210K

Quantization options

How Nemotron Cascade 2 30B A3B (30B params) fits at each quantization level on AMD Instinct MI210 64GB (64.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	11.7 GB	Low	A79
Q3_K_S	3	14.7 GB	Low	A80
NVFP4	4	16.8 GB	Medium	A80
Q4_K_M	4	18.3 GB	Medium	A81
Q5_K_M	5	21.6 GB	High	A82
Q6_K	6	24.6 GB	High	A82
Q8_0Best for your GPU	8	32.1 GB	Very High	A84
F16	16	61.5 GB	Maximum	F0

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 MI210 64GB can run

Model	Params	Grade	Decode
Qwen3-Coder 30B A3B Instruct	30.5B	S	168.4 tok/s
Qwen 3.6 35B A3B	35B	S	141.5 tok/s
Qwen 3.5 35B A3B	35B	S	153.9 tok/s
Qwen 3 32B	32B	S	62.1 tok/s
Qwen 3 30B A3B	30.5B	S	168.4 tok/s

Frequently asked questions

Can AMD Instinct MI210 64GB run Nemotron Cascade 2 30B A3B?

Yes, AMD Instinct MI210 64GB can run Nemotron Cascade 2 30B A3B with a S grade (Runs well). Expected decode speed: 172.2 tok/s.

How much VRAM does Nemotron Cascade 2 30B A3B need?

Nemotron Cascade 2 30B A3B (30B parameters) requires approximately 28.5 GB of memory with Q4_K_M quantization.

What is the best quantization for Nemotron Cascade 2 30B A3B?

The recommended quantization for Nemotron Cascade 2 30B A3B is Q4_K_M, which balances quality and memory efficiency.

What speed will Nemotron Cascade 2 30B A3B run at on AMD Instinct MI210 64GB?

On AMD Instinct MI210 64GB, Nemotron Cascade 2 30B A3B achieves approximately 172.2 tokens per second decode speed with a time-to-first-token of 1124ms using Q4_K_M quantization.

Can AMD Instinct MI210 64GB run Nemotron Cascade 2 30B A3B for coding?

For coding workloads, Nemotron Cascade 2 30B A3B on AMD Instinct MI210 64GB receives a S grade with 172.2 tok/s and 210K context.

What context window can Nemotron Cascade 2 30B A3B use on AMD Instinct MI210 64GB?

On AMD Instinct MI210 64GB, Nemotron Cascade 2 30B A3B can safely use up to 210K tokens of context. The model's official context limit is 262K, but available memory constrains the safe maximum.

See all results for AMD Instinct MI210 64GB See all hardware for Nemotron Cascade 2 30B A3B

Embed this result▼

Paste this snippet into any page to show a live fit card.

<iframe src="https://willitrunai.com/embed/nemotron-cascade-2-30b-a3b-on-instinct-mi210-64gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview:

Workload

Grade

Fit

Decode

TTFT

Context

Chat

Runs well

172.2 tok/s

613 ms

210K

Coding

Runs well

172.2 tok/s

1124 ms

210K

Agentic Coding

Runs well

172.2 tok/s

1635 ms

210K

Reasoning

Runs well

172.2 tok/s

1329 ms

210K

RAG

Runs well

172.2 tok/s

2044 ms

210K

Quantization options

How Nemotron Cascade 2 30B A3B (30B params) fits at each quantization level on AMD Instinct MI210 64GB (64.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	11.7 GB	Low	A79
Q3_K_S	3	14.7 GB	Low	A80
NVFP4	4	16.8 GB	Medium	A80
Q4_K_M	4	18.3 GB	Medium	A81
Q5_K_M	5	21.6 GB	High	A82
Q6_K	6	24.6 GB	High	A82
Q8_0Best for your GPU	8	32.1 GB	Very High	A84
F16	16	61.5 GB	Maximum	F0

Model

Params

Grade

Decode

Capabilities

Qwen3-Coder 30B A3B Instruct

30.5B

168.4 tok/s

Qwen 3.6 35B A3B

35B

141.5 tok/s

Qwen 3.5 35B A3B

35B

153.9 tok/s

Qwen 3 32B

32B

62.1 tok/s

Qwen 3 30B A3B