Can Gemma 3 27B run on NVIDIA L40S 48GB?

YES — Runs Great

S87Excellent

Estimated from fit model

Gemma 3 27B needs ~33.7 GB VRAM. NVIDIA L40S 48GB has 48.0 GB. With Q4_K_M quantization, expect ~43 tok/s.

Runtime: OllamaCapacity: RoomyBandwidth: HighStack: BasicBottleneck: 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) — 33.7 GB, 43.0 tok/s, Runs well

33.7 GB required48.0 GB available

70% VRAM used

Fit status

Runs well

Decode

43.0 tok/s

TTFT

4506 ms

Safe context

36K

Memory

33.7 GB / 48.0 GB

Memory breakdown

Weights16.5 GB

KV Cache11.2 GB

Runtime1.2 GB

Headroom4.8 GB

See how fast it feels

See how fast it feelsGemma 3 27B on NVIDIA L40S 48GB
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: 43.0 tok/s decode · 4.5s TTFT (warm) · 107 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	A	Runs well	43.0 tok/s	2458 ms	36K
Coding	S	Runs well	43.0 tok/s	4506 ms	36K
Agentic Coding	A	Tight fit	43.0 tok/s	6554 ms	36K
Reasoning	S	Runs well	43.0 tok/s	5325 ms	36K
RAG	A	Tight fit	43.0 tok/s	8193 ms	36K

Quantization options

How Gemma 3 27B (27B params) fits at each quantization level on NVIDIA L40S 48GB (48.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	10.5 GB	Low	A76
Q3_K_S	3	13.2 GB	Low	A76
NVFP4	4	15.1 GB	Medium	A77
Q4_K_M	4	16.5 GB	Medium	A77
Q5_K_M	5	19.4 GB	High	A78
Q6_K	6	22.1 GB	High	A79
Q8_0Best for your GPU	8	28.9 GB	Very High	A81
F16	16	55.4 GB	Maximum	F0

Get started

Copy-paste commands to run Gemma 3 27B on your machine.

Run

ollama run gemma3

Your hardware

More models your NVIDIA L40S 48GB can run

Model	Params	Grade	Decode
Qwen3-Coder 30B A3B Instruct	30.5B	S	101.9 tok/s
Qwen 3.6 35B A3B	35B	S	91.6 tok/s
Qwen3-VL 30B A3B Instruct	30B	S	105.4 tok/s
Qwen 3.5 35B A3B	35B	S	99.7 tok/s
Qwen 3 32B	32B	S	37.5 tok/s

Frequently asked questions

Can NVIDIA L40S 48GB run Gemma 3 27B?

Yes, NVIDIA L40S 48GB can run Gemma 3 27B with a S grade (Runs well). Expected decode speed: 43.0 tok/s.

How much VRAM does Gemma 3 27B need?

Gemma 3 27B (27B parameters) requires approximately 33.7 GB of memory with Q4_K_M quantization.

What is the best quantization for Gemma 3 27B?

The recommended quantization for Gemma 3 27B is Q4_K_M, which balances quality and memory efficiency.

What speed will Gemma 3 27B run at on NVIDIA L40S 48GB?

On NVIDIA L40S 48GB, Gemma 3 27B achieves approximately 43.0 tokens per second decode speed with a time-to-first-token of 4506ms using Q4_K_M quantization.

Can NVIDIA L40S 48GB run Gemma 3 27B for coding?

For coding workloads, Gemma 3 27B on NVIDIA L40S 48GB receives a S grade with 43.0 tok/s and 36K context.

What context window can Gemma 3 27B use on NVIDIA L40S 48GB?

On NVIDIA L40S 48GB, Gemma 3 27B can safely use up to 36K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.

See all results for NVIDIA L40S 48GB See all hardware for Gemma 3 27B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/gemma-3-27b-on-l40s-48gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: