Can Gemma 4 26B A4B run on NVIDIA DGX Spark 128GB?

YES — With F16

A84Great

Estimated from fit model

Gemma 4 26B A4B needs ~69.6 GB VRAM. NVIDIA DGX Spark 128GB has 0 MB. With F16 quantization, expect ~11 tok/s.

Runtime: OllamaCapacity: RoomyBandwidth: 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.

Gemma 4 26B A4B at Q4_K_M needs 20.2 GB — too much for NVIDIA DGX Spark 128GB (0.0 GB). Runs at F16 (69.6 GB) with maximum quality. 8 quantization levels fit.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 33.3 GB, 26.6 tok/s, Runs well

33.3 GB required108.8 GB available

31% VRAM used

Fit status

Runs well

Decode

26.6 tok/s

TTFT

7278 ms

Safe context

256K

Memory

33.3 GB / 108.8 GB

Memory breakdown

Weights15.4 GB

KV Cache3.7 GB

Runtime1.2 GB

Headroom13.1 GB

See how fast it feels

See how fast it feelsGemma 4 26B A4B on NVIDIA DGX Spark 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: 26.6 tok/s decode · 7.3s TTFT (warm) · 67 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

Shared-memory contention still exists

The OS, browser, and inference runtime all compete for the same physical memory pool, so real-world headroom is less forgiving than raw capacity suggests.

Best improvement path

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	A	Runs well	26.6 tok/s	3970 ms	256K
Coding	F	Too heavy	4.6 tok/s	42458 ms	4K
Agentic Coding	A	Runs well	26.6 tok/s	10587 ms	256K
Reasoning	A	Runs well	26.6 tok/s	8602 ms	256K
RAG	A	Runs well	26.6 tok/s	13234 ms	256K

Quantization options

How Gemma 4 26B A4B (25.200000762939453B params) fits at each quantization level on NVIDIA DGX Spark 128GB (92.2 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	9.8 GB	Low	A75
Q3_K_S	3	12.3 GB	Low	A75
NVFP4	4	14.1 GB	Medium	A75
Q4_K_M	4	15.4 GB	Medium	A75
Q5_K_M	5	18.1 GB	High	A76
Q6_K	6	20.7 GB	High	A76
Q8_0	8	27.0 GB	Very High	A77
F16Best for your GPU	16	51.7 GB	Maximum	A83

Get started

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

Run

ollama run gemma4:26b

Upgrade-Optionen

Hardware, die Gemma 4 26B A4B gut ausführt

NVIDIA H200 141GBGünstige Wahl

141 GB VRAM (+13)4800 GB/s (+4527)

Raises estimated decode speed by about 2361%.654.7 tok/s Dekodierung

Raises estimated decode speed by about 2361%.

Adds memory headroom for longer context windows and future model growth.

ca. $30,000 MSRP

NVIDIA H200 PCIe 141GBBestes Preis-Leistungs-Verhältnis

141 GB VRAM (+13)4800 GB/s (+4527)

Raises estimated decode speed by about 2361%.654.7 tok/s Dekodierung

Raises estimated decode speed by about 2361%.

Adds memory headroom for longer context windows and future model growth.

ca. $30,000 MSRP

NVIDIA B200 180GBNVIDIA-Upgrade

180 GB VRAM (+52)8000 GB/s (+7727)

Raises estimated decode speed by about 4002%.1091.2 tok/s Dekodierung

Raises estimated decode speed by about 4002%.

Adds memory headroom for longer context windows and future model growth.

ca. $30,000 MSRP

Frequently asked questions

Can NVIDIA DGX Spark 128GB run Gemma 4 26B A4B?

Yes, NVIDIA DGX Spark 128GB can run Gemma 4 26B A4B at F16 quantization (Runs well). The recommended Q4_K_M requires 20.2 GB which exceeds available memory, but at F16 it needs only 69.6 GB. Expected decode speed: 11.1 tok/s.

How much VRAM does Gemma 4 26B A4B need?

Gemma 4 26B A4B (25.200000762939453B parameters) requires approximately 20.2 GB at Q4_K_M quantization. On NVIDIA DGX Spark 128GB, it fits at F16 using 69.6 GB.

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

The recommended quantization is Q4_K_M, but on NVIDIA DGX Spark 128GB the best fitting quantization is F16, which uses 69.6 GB.

What speed will Gemma 4 26B A4B run at on NVIDIA DGX Spark 128GB?

On NVIDIA DGX Spark 128GB, Gemma 4 26B A4B achieves approximately 11.1 tokens per second decode speed with a time-to-first-token of 17472ms using F16 quantization.

Can NVIDIA DGX Spark 128GB run Gemma 4 26B A4B for coding?

For coding workloads, Gemma 4 26B A4B on NVIDIA DGX Spark 128GB receives a F grade with 4.6 tok/s and 4K context.

What context window can Gemma 4 26B A4B use on NVIDIA DGX Spark 128GB?

On NVIDIA DGX Spark 128GB, Gemma 4 26B A4B can safely use up to 187K tokens of context at F16 quantization. The model's official context limit is 256K, but available memory constrains the safe maximum.

Is unified memory on NVIDIA DGX Spark 128GB as fast as VRAM for Gemma 4 26B A4B?

Not always. NVIDIA DGX Spark 128GB can often fit larger models thanks to unified memory, but a discrete GPU with dedicated high-bandwidth VRAM may still decode faster once the model fits. For this combination, the important distinction is capacity versus sustained throughput.

See all results for NVIDIA DGX Spark 128GB 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-dgx-spark-128gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: