Can Nemotron Cascade 2 30B A3B run on Tesla P40 24GB?

YES — With Offload

S87Excellent

Estimated from fit model

Nemotron Cascade 2 30B A3B needs ~24.5 GB VRAM. Tesla P40 24GB has 24.0 GB. With Q4_K_M quantization, expect ~22 tok/s.

Runtime: llama.cppCapacity: OffloadBandwidth: LowStack: 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) — 24.5 GB, 21.9 tok/s, Runs with offload (needs ~0.4 GB host RAM)

24.5 GB required24.0 GB available

102% VRAM needed

0.5 GB over capacity — needs offload or smaller quantization

Fit status

Runs with offload (needs ~0.4 GB host RAM)

Decode

21.9 tok/s

TTFT

8824 ms

Safe context

13K

Memory

24.5 GB / 24.0 GB

Memory breakdown

Weights18.3 GB

KV Cache2.9 GB

Runtime0.9 GB

Headroom2.4 GB

See how fast it feels

See how fast it feelsNemotron Cascade 2 30B A3B on Tesla P40 24GB
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: 21.9 tok/s decode · 8.8s TTFT (warm) · 55 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

Very little memory headroom

You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.

Older PCIe generation

PCIe 3.0 is workable, but it compounds the penalty when you offload heavily or try to scale across multiple cards.

Best improvement path

Buy headroom, not only minimum fit

A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	S	Runs with offload	31.6 tok/s	3346 ms	13K
Coding	S	Runs with offload (needs ~0.4 GB host RAM)	21.9 tok/s	8824 ms	13K
Agentic Coding	A	Very compromised (needs ~2.3 GB host RAM)	17.1 tok/s	16443 ms	13K
Reasoning	S	Runs with offload (needs ~0.4 GB host RAM)	21.9 tok/s	10428 ms	13K
RAG	A	Very compromised (needs ~2.3 GB host RAM)	17.1 tok/s	20554 ms	13K

Quantization options

How Nemotron Cascade 2 30B A3B (30B params) fits at each quantization level on Tesla P40 24GB (24.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	11.7 GB	Low	S88
Q3_K_S	3	14.7 GB	Low	S88
NVFP4	4	16.8 GB	Medium	S87
Q4_K_MBest for your GPU	4	18.3 GB	Medium	S87
Q5_K_M	5	21.6 GB	High	F0
Q6_K	6	24.6 GB	High	F0
Q8_0	8	32.1 GB	Very High	F0
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 Tesla P40 24GB can run

Model	Params	Grade	Decode
Qwen3-Coder 30B A3B Instruct	30.5B	S	30.9 tok/s
Qwen 3.6 35B A3B	35B	A	12.7 tok/s
Qwen 3.5 35B A3B	35B	A	17.1 tok/s
Qwen 3 32B	32B	A	6.5 tok/s
Qwen 3 30B A3B	30.5B	S	30.9 tok/s

Frequently asked questions

Can Tesla P40 24GB run Nemotron Cascade 2 30B A3B?

Yes, Tesla P40 24GB can run Nemotron Cascade 2 30B A3B with a S grade (Runs with offload (needs ~0.4 GB host RAM)). Expected decode speed: 21.9 tok/s.

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

Nemotron Cascade 2 30B A3B (30B parameters) requires approximately 24.5 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 Tesla P40 24GB?

On Tesla P40 24GB, Nemotron Cascade 2 30B A3B achieves approximately 21.9 tokens per second decode speed with a time-to-first-token of 8824ms using Q4_K_M quantization.

Can Tesla P40 24GB run Nemotron Cascade 2 30B A3B for coding?

For coding workloads, Nemotron Cascade 2 30B A3B on Tesla P40 24GB receives a S grade with 21.9 tok/s and 13K context.

What context window can Nemotron Cascade 2 30B A3B use on Tesla P40 24GB?

On Tesla P40 24GB, Nemotron Cascade 2 30B A3B can safely use up to 13K tokens of context. The model's official context limit is 262K, but available memory constrains the safe maximum.

What should I upgrade first if Nemotron Cascade 2 30B A3B feels slow on Tesla P40 24GB?

Buy headroom, not only minimum fit. A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.

See all results for Tesla P40 24GB 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-tesla-p40-24gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: