Can Nemotron 3 Nano 30B run on AMD Instinct MI300A 128GB?

YES — Runs Great

S88Excellent

Estimated from fit model

Nemotron 3 Nano 30B needs ~34.4 GB VRAM. AMD Instinct MI300A 128GB has 128.0 GB. With Q4_K_M quantization, expect ~218 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) — 34.4 GB, 217.9 tok/s, Runs well

34.4 GB required128.0 GB available

27% VRAM used

Fit status

Runs well

Decode

217.9 tok/s

TTFT

888 ms

Safe context

131K

Memory

34.4 GB / 128.0 GB

Memory breakdown

Weights18.3 GB

KV Cache2.4 GB

Runtime0.9 GB

Headroom12.8 GB

See how fast it feels

See how fast it feelsNemotron 3 Nano 30B on AMD Instinct MI300A 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: 217.9 tok/s decode · 888ms TTFT (warm) · 545 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	217.9 tok/s	485 ms	131K
Coding	S	Runs well	217.9 tok/s	888 ms	131K
Agentic Coding	S	Runs well	217.9 tok/s	1292 ms	131K
Reasoning	S	Runs well	217.9 tok/s	1050 ms	131K
RAG	S	Runs well	217.9 tok/s	1615 ms	131K

Inference speed

Nemotron 3 Nano 30B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Nemotron 3 Nano 30B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~71 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.

GPU / Mac	Memory	Quant	Speed (tok/s)	Fits?
RTX 5090 32GB	32 GB	Q4_K_M	70.5	Fits
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	38.1	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	38.1	Fits
RTX 4090 24GB	24 GB	Q4_K_M	32.8	Offloads
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	32.7	Fits
RX 7900 XTX 24GB	24 GB	Q4_K_M	30.3	Offloads
RTX 3090 24GB	24 GB	Q4_K_M	28.0	Offloads
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	27.3	Fits
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	25.8	Fits
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	24.0	Fits
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	14.1	Fits
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	12.9	Fits
RTX 4080 Super 16GB	16 GB	Q4_K_M	11.9	Too big
RTX 4070 12GB	12 GB	Q4_K_M	4.2	Too big
RTX 3060 12GB	12 GB	Q4_K_M	2.6	Too big
RTX 4060 8GB	8 GB	Q4_K_M	2.0	Too big

Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.

Quantization options

How Nemotron 3 Nano 30B (30B params) fits at each quantization level on AMD Instinct MI300A 128GB (128.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	11.7 GB	Low	A79
Q3_K_S	3	14.7 GB	Low	A79
NVFP4	4	16.8 GB	Medium	A79
Q4_K_M	4	18.3 GB	Medium	A79
Q5_K_M	5	21.6 GB	High	A79
Q6_K	6	24.6 GB	High	A80
Q8_0	8	32.1 GB	Very High	A81
F16Best for your GPU	16	61.5 GB	Maximum	S86

Get started

Copy-paste commands to run Nemotron 3 Nano 30B on your machine.

Run

ollama run nemotron-nano:30b

Your hardware

More models your AMD Instinct MI300A 128GB can run

Model	Params	Grade	Decode
Devstral 2 123B Instruct	123B	S	53.8 tok/s
Qwen3-Coder 30B A3B Instruct	30.5B	S	561 tok/s
Qwen 3.5 122B A10B	122B	S	149.2 tok/s
Qwen 3.6 35B A3B	35B	S	471.5 tok/s
Qwen 3.5 35B A3B	35B	S	512.7 tok/s

Frequently asked questions

Can AMD Instinct MI300A 128GB run Nemotron 3 Nano 30B?

Yes, AMD Instinct MI300A 128GB can run Nemotron 3 Nano 30B with a S grade (Runs well). Expected decode speed: 217.9 tok/s.

How much VRAM does Nemotron 3 Nano 30B need?

Nemotron 3 Nano 30B (30B parameters) requires approximately 34.4 GB of memory with Q4_K_M quantization.

What is the best quantization for Nemotron 3 Nano 30B?

The recommended quantization for Nemotron 3 Nano 30B is Q4_K_M, which balances quality and memory efficiency.

What speed will Nemotron 3 Nano 30B run at on AMD Instinct MI300A 128GB?

On AMD Instinct MI300A 128GB, Nemotron 3 Nano 30B achieves approximately 217.9 tokens per second decode speed with a time-to-first-token of 888ms using Q4_K_M quantization.

Can AMD Instinct MI300A 128GB run Nemotron 3 Nano 30B for coding?

For coding workloads, Nemotron 3 Nano 30B on AMD Instinct MI300A 128GB receives a S grade with 217.9 tok/s and 131K context.

What context window can Nemotron 3 Nano 30B use on AMD Instinct MI300A 128GB?

On AMD Instinct MI300A 128GB, Nemotron 3 Nano 30B can safely use up to 131K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.

See all results for AMD Instinct MI300A 128GB See all hardware for Nemotron 3 Nano 30B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/nemotron-3-nano-30b-on-instinct-mi300a-128gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: