Can Qwen3-Coder-Next run on NVIDIA DGX Spark 128GB?

YES — With Q8_0

S86Excellent

Estimated from fit model

Qwen3-Coder-Next needs ~101.3 GB VRAM. NVIDIA DGX Spark 128GB has 0 MB. With Q8_0 quantization, expect ~7 tok/s.

Runtime: OllamaCapacity: TightBandwidth: 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.

Qwen3-Coder-Next at Q4_K_M needs 51.5 GB — too much for NVIDIA DGX Spark 128GB (0.0 GB). Runs at Q8_0 (101.3 GB) with very high quality. 7 quantization levels fit.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 64.5 GB, 11.1 tok/s, Runs well

64.5 GB required108.8 GB available

59% VRAM used

Fit status

Runs well

Decode

11.1 tok/s

TTFT

17502 ms

Safe context

256K

Memory

64.5 GB / 108.8 GB

Memory breakdown

Weights48.8 GB

KV Cache1.5 GB

Runtime1.2 GB

Headroom13.1 GB

See how fast it feels

See how fast it feelsQwen3-Coder-Next 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: 11.1 tok/s decode · 17.5s TTFT (warm) · 28 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.

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.

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.

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	Runs well	11.1 tok/s	9547 ms	256K
Coding	F	Too heavy	2.0 tok/s	96800 ms	4K
Agentic Coding	S	Runs well	11.1 tok/s	25458 ms	256K
Reasoning	S	Runs well	11.1 tok/s	20685 ms	256K
RAG	S	Runs well	11.1 tok/s	31822 ms	256K

Quantization options

How Qwen3-Coder-Next (80B params) fits at each quantization level on NVIDIA DGX Spark 128GB (92.2 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	31.2 GB	Low	A83
Q3_K_S	3	39.2 GB	Low	S85
NVFP4	4	44.8 GB	Medium	S87
Q4_K_M	4	48.8 GB	Medium	S87
Q5_K_M	5	57.6 GB	High	S88
Q6_KBest for your GPU	6	65.6 GB	High	S88
Q8_0	8	85.6 GB	Very High	F0
F16	16	164.0 GB	Maximum	F0

Get started

Copy-paste commands to run Qwen3-Coder-Next on your machine.

Run

ollama run qwen3-coder-next

アップグレードオプション

Qwen3-Coder-Next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 2353%.272.3 tok/sデコード

Raises estimated decode speed by about 2353%.

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 2353%.272.3 tok/sデコード

Raises estimated decode speed by about 2353%.

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 3988%.453.8 tok/sデコード

Raises estimated decode speed by about 3988%.

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

〜$30,000 MSRP

Frequently asked questions

Can NVIDIA DGX Spark 128GB run Qwen3-Coder-Next?

Yes, NVIDIA DGX Spark 128GB can run Qwen3-Coder-Next at Q8_0 quantization (Tight fit). The recommended Q4_K_M requires 51.5 GB which exceeds available memory, but at Q8_0 it needs only 101.3 GB. Expected decode speed: 6.9 tok/s.

How much VRAM does Qwen3-Coder-Next need?

Qwen3-Coder-Next (80B parameters) requires approximately 51.5 GB at Q4_K_M quantization. On NVIDIA DGX Spark 128GB, it fits at Q8_0 using 101.3 GB.

What is the best quantization for Qwen3-Coder-Next?

The recommended quantization is Q4_K_M, but on NVIDIA DGX Spark 128GB the best fitting quantization is Q8_0, which uses 101.3 GB.

What speed will Qwen3-Coder-Next run at on NVIDIA DGX Spark 128GB?

On NVIDIA DGX Spark 128GB, Qwen3-Coder-Next achieves approximately 6.9 tokens per second decode speed with a time-to-first-token of 27910ms using Q8_0 quantization.

Can NVIDIA DGX Spark 128GB run Qwen3-Coder-Next for coding?

For coding workloads, Qwen3-Coder-Next on NVIDIA DGX Spark 128GB receives a F grade with 2.0 tok/s and 4K context.

What context window can Qwen3-Coder-Next use on NVIDIA DGX Spark 128GB?

On NVIDIA DGX Spark 128GB, Qwen3-Coder-Next can safely use up to 98K tokens of context at Q8_0 quantization. The model's official context limit is 256K, but available memory constrains the safe maximum.

What should I upgrade first if Qwen3-Coder-Next 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 Qwen3-Coder-Next?

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 Qwen3-Coder-Next

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/qwen-3-coder-next-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: