Can Qwen 2.5 Coder 32B run on NVIDIA DGX Spark 128GB?

YES — With F16

A75Great

Estimated from fit model

Qwen 2.5 Coder 32B needs ~83.8 GB VRAM. NVIDIA DGX Spark 128GB has 0 MB. With F16 quantization, expect ~4 tok/s.

Runtime: OllamaCapacity: RoomyBandwidth: LowStack: BasicBottleneck: Memory bandwidth

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 32B at Q4_K_M needs 24.6 GB — too much for NVIDIA DGX Spark 128GB (0.0 GB). Runs at F16 (83.8 GB) with maximum quality. 8 quantization levels fit.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 37.7 GB, 9.1 tok/s, Runs well

37.7 GB required108.8 GB available

35% VRAM used

Fit status

Runs well

Decode

9.1 tok/s

TTFT

21362 ms

Safe context

131K

Memory

37.7 GB / 108.8 GB

Memory breakdown

Weights19.5 GB

KV Cache3.9 GB

Runtime1.2 GB

Headroom13.1 GB

See how fast it feels

See how fast it feelsQwen 2.5 Coder 32B 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: 9.1 tok/s decode · 21.4s TTFT (warm) · 23 tok/s prefill

What limits this setup

The model fits in shared memory, but shared-memory bandwidth is now the real limiter.

Fit does not mean dedicated-VRAM speed

Unified or shared memory can make a model technically fit, but sustained tokens per second may still trail a discrete high-bandwidth GPU with less total memory.

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

Prioritize bandwidth, not only capacity

If this workload feels slow, the next useful step is often a GPU tier with materially faster memory bandwidth rather than only a small bump in capacity.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	B	Runs well	9.1 tok/s	11652 ms	131K
Coding	F	Too heavy	2.0 tok/s	96800 ms	4K
Agentic Coding	A	Runs well	9.1 tok/s	31072 ms	131K
Reasoning	B	Runs well	9.1 tok/s	25246 ms	131K
RAG	A	Runs well	9.1 tok/s	38841 ms	131K

Quantization options

How Qwen 2.5 Coder 32B (32B params) fits at each quantization level on NVIDIA DGX Spark 128GB (92.2 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	12.5 GB	Low	B68
Q3_K_S	3	15.7 GB	Low	B68
NVFP4	4	17.9 GB	Medium	B68
Q4_K_M	4	19.5 GB	Medium	B69
Q5_K_M	5	23.0 GB	High	B69
Q6_K	6	26.2 GB	High	B70
Q8_0	8	34.2 GB	Very High	A71
F16Best for your GPU	16	65.6 GB	Maximum	A76

Get started

Copy-paste commands to run Qwen 2.5 Coder 32B on your machine.

Run

ollama run qwen2.5-coder

アップグレードオプション

Qwen 2.5 Coder 32Bを快適に動かすハードウェア

NVIDIA H200 141GBコスパ重視

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

Raises estimated decode speed by about 2352%.223.1 tok/sデコード

Raises estimated decode speed by about 2352%.

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

〜$30,000 MSRP

NVIDIA H200 PCIe 141GBコスパ最良

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

Raises estimated decode speed by about 2352%.223.1 tok/sデコード

Raises estimated decode speed by about 2352%.

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

〜$30,000 MSRP

NVIDIA B200 180GBNVIDIAアップグレード

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

Raises estimated decode speed by about 3986%.371.8 tok/sデコード

Raises estimated decode speed by about 3986%.

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

〜$30,000 MSRP

Frequently asked questions

Can NVIDIA DGX Spark 128GB run Qwen 2.5 Coder 32B?

Yes, NVIDIA DGX Spark 128GB can run Qwen 2.5 Coder 32B at F16 quantization (Runs well). The recommended Q4_K_M requires 24.6 GB which exceeds available memory, but at F16 it needs only 83.8 GB. Expected decode speed: 3.8 tok/s.

How much VRAM does Qwen 2.5 Coder 32B need?

Qwen 2.5 Coder 32B (32B parameters) requires approximately 24.6 GB at Q4_K_M quantization. On NVIDIA DGX Spark 128GB, it fits at F16 using 83.8 GB.

What is the best quantization for Qwen 2.5 Coder 32B?

The recommended quantization is Q4_K_M, but on NVIDIA DGX Spark 128GB the best fitting quantization is F16, which uses 83.8 GB.

What speed will Qwen 2.5 Coder 32B run at on NVIDIA DGX Spark 128GB?

On NVIDIA DGX Spark 128GB, Qwen 2.5 Coder 32B achieves approximately 3.8 tokens per second decode speed with a time-to-first-token of 51279ms using F16 quantization.

Can NVIDIA DGX Spark 128GB run Qwen 2.5 Coder 32B for coding?

For coding workloads, Qwen 2.5 Coder 32B on NVIDIA DGX Spark 128GB receives a F grade with 2.0 tok/s and 4K context.

What context window can Qwen 2.5 Coder 32B use on NVIDIA DGX Spark 128GB?

On NVIDIA DGX Spark 128GB, Qwen 2.5 Coder 32B can safely use up to 119K tokens of context at F16 quantization. The model's official context limit is 131K, but available memory constrains the safe maximum.

What should I upgrade first if Qwen 2.5 Coder 32B feels slow on NVIDIA DGX Spark 128GB?

Prioritize bandwidth, not only capacity. If this workload feels slow, the next useful step is often a GPU tier with materially faster memory bandwidth rather than only a small bump in capacity.

Is unified memory on NVIDIA DGX Spark 128GB as fast as VRAM for Qwen 2.5 Coder 32B?

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 Qwen 2.5 Coder 32B

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-32b-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: