Is unified memory on NVIDIA DGX Spark 128GB as fast as VRAM for Qwen 2.5 Coder 1.5B?

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.

Can Qwen 2.5 Coder 1.5B run on NVIDIA DGX Spark 128GB?

YES — With F16

B59Good

Estimated from fit model

Qwen 2.5 Coder 1.5B needs ~17.8 GB VRAM. NVIDIA DGX Spark 128GB has 0 MB. With F16 quantization, expect ~21 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.

Qwen 2.5 Coder 1.5B at Q4_K_M needs 2.5 GB — too much for NVIDIA DGX Spark 128GB (0.0 GB). Runs at F16 (17.8 GB) with maximum quality. 8 quantization levels fit.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 15.6 GB, 21.0 tok/s, Runs well

15.6 GB required108.8 GB available

14% VRAM used

Fit status

Runs well

Decode

21.0 tok/s

TTFT

9219 ms

Safe context

33K

Memory

15.6 GB / 108.8 GB

Memory breakdown

Weights0.9 GB

KV Cache0.4 GB

Runtime1.2 GB

Headroom13.1 GB

See how fast it feels

See how fast it feelsQwen 2.5 Coder 1.5B 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: 21.0 tok/s decode · 9.2s TTFT (warm) · 53 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	F	Too heavy	21.0 tok/s	5029 ms	4K
Coding	F	Too heavy	21.0 tok/s	9219 ms	4K
Agentic Coding	F	Too heavy	21.0 tok/s	13410 ms	4K
Reasoning	F	Too heavy	21.0 tok/s	10895 ms	4K
RAG	F	Too heavy	21.0 tok/s	16762 ms	4K

Quantization options

How Qwen 2.5 Coder 1.5B (1.5B params) fits at each quantization level on NVIDIA DGX Spark 128GB (92.2 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	0.6 GB	Low	B58
Q3_K_S	3	0.7 GB	Low	B58
NVFP4	4

Get started

Copy-paste commands to run Qwen 2.5 Coder 1.5B on your machine.

Run

ollama run qwen2.5-coder:1.5b

Upgrade options

Hardware that runs Qwen 2.5 Coder 1.5B well

Mac Studio M3 Ultra 256GBBudget pick

256 GB Unified (+128)819 GB/s (+546)

Adds memory headroom for longer context windows and future model growth.21 tok/s decode

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

~$6,999 MSRP

Frequently asked questions

Can NVIDIA DGX Spark 128GB run Qwen 2.5 Coder 1.5B?

Yes, NVIDIA DGX Spark 128GB can run Qwen 2.5 Coder 1.5B at F16 quantization (Runs well). The recommended Q4_K_M requires 2.5 GB which exceeds available memory, but at F16 it needs only 17.8 GB. Expected decode speed: 21.0 tok/s.

How much VRAM does Qwen 2.5 Coder 1.5B need?

Qwen 2.5 Coder 1.5B (1.5B parameters) requires approximately 2.5 GB at Q4_K_M quantization. On NVIDIA DGX Spark 128GB, it fits at F16 using 17.8 GB.

What is the best quantization for Qwen 2.5 Coder 1.5B?

The recommended quantization is Q4_K_M, but on NVIDIA DGX Spark 128GB the best fitting quantization is F16, which uses 17.8 GB.

What speed will Qwen 2.5 Coder 1.5B run at on NVIDIA DGX Spark 128GB?

On NVIDIA DGX Spark 128GB, Qwen 2.5 Coder 1.5B achieves approximately 21.0 tokens per second decode speed with a time-to-first-token of 9219ms using F16 quantization.

Can NVIDIA DGX Spark 128GB run Qwen 2.5 Coder 1.5B for coding?

For coding workloads, Qwen 2.5 Coder 1.5B on NVIDIA DGX Spark 128GB receives a F grade with 21.0 tok/s and 4K context.

What context window can Qwen 2.5 Coder 1.5B use on NVIDIA DGX Spark 128GB?

On NVIDIA DGX Spark 128GB, Qwen 2.5 Coder 1.5B can safely use up to 33K tokens of context at F16 quantization. The model's official context limit is 33K, but available memory constrains the safe maximum.

See all results for NVIDIA DGX Spark 128GB See all hardware for Qwen 2.5 Coder 1.5B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/qwen-2.5-coder-1.5b-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: