Can Gemma 4 26B A4B run on Tesla P40 24GB?

YES — Tight Fit

S86Excellent

Estimated from fit model

Gemma 4 26B A4B needs ~22.6 GB VRAM. Tesla P40 24GB has 24.0 GB. With Q4_K_M quantization, expect ~33 tok/s.

Runtime: OllamaCapacity: TightBandwidth: LowStack: 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) — 22.6 GB, 33.1 tok/s, Tight fit

22.6 GB required24.0 GB available

94% VRAM used

Fit status

Tight fit

Decode

33.1 tok/s

TTFT

5840 ms

Safe context

22K

Memory

22.6 GB / 24.0 GB

Memory breakdown

Weights15.4 GB

KV Cache3.7 GB

Runtime1.2 GB

Headroom2.4 GB

See how fast it feels

See how fast it feelsGemma 4 26B A4B 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: 33.1 tok/s decode · 5.8s TTFT (warm) · 83 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	Tight fit	33.1 tok/s	3186 ms	22K
Coding	S	Tight fit	33.1 tok/s	5840 ms	22K
Agentic Coding	A	Very compromised (needs ~1.3 GB host RAM)	19.8 tok/s	14234 ms	22K
Reasoning	S	Tight fit	33.1 tok/s	6902 ms	22K
RAG	A	Very compromised (needs ~1.3 GB host RAM)	19.8 tok/s	17792 ms	22K

Quantization options

How Gemma 4 26B A4B (25.200000762939453B params) fits at each quantization level on Tesla P40 24GB (24.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	9.8 GB	Low	A84
Q3_K_S	3	12.3 GB	Low	S85
NVFP4	4	14.1 GB	Medium	S85
Q4_K_M	4	15.4 GB	Medium	A85
Q5_K_MBest for your GPU	5	18.1 GB	High	A84
Q6_K	6	20.7 GB	High	F0
Q8_0	8	27.0 GB	Very High	F0
F16	16	51.7 GB	Maximum	F0

Get started

Copy-paste commands to run Gemma 4 26B A4B on your machine.

Run

ollama run gemma4:26b

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 3.5 27B	27B	S	13.4 tok/s
Qwen 3.6 27B	27B	S	13.4 tok/s
Qwen3-VL 30B A3B Instruct	30B	S	31.9 tok/s
Qwen 3.5 35B A3B	35B	A	16.7 tok/s

Frequently asked questions

Can Tesla P40 24GB run Gemma 4 26B A4B?

Yes, Tesla P40 24GB can run Gemma 4 26B A4B with a S grade (Tight fit). Expected decode speed: 33.1 tok/s.

How much VRAM does Gemma 4 26B A4B need?

Gemma 4 26B A4B (25.200000762939453B parameters) requires approximately 22.6 GB of memory with Q4_K_M quantization.

What is the best quantization for Gemma 4 26B A4B?

The recommended quantization for Gemma 4 26B A4B is Q4_K_M, which balances quality and memory efficiency.

What speed will Gemma 4 26B A4B run at on Tesla P40 24GB?

On Tesla P40 24GB, Gemma 4 26B A4B achieves approximately 33.1 tokens per second decode speed with a time-to-first-token of 5840ms using Q4_K_M quantization.

Can Tesla P40 24GB run Gemma 4 26B A4B for coding?

For coding workloads, Gemma 4 26B A4B on Tesla P40 24GB receives a S grade with 33.1 tok/s and 22K context.

What context window can Gemma 4 26B A4B use on Tesla P40 24GB?

On Tesla P40 24GB, Gemma 4 26B A4B can safely use up to 22K tokens of context. The model's official context limit is 256K, but available memory constrains the safe maximum.

What should I upgrade first if Gemma 4 26B A4B 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 Gemma 4 26B A4B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/gemma-4-26b-a4b-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: