Can Qwen 3.5 122B A10B run on NVIDIA DGX Spark 128GB?

YES — Tight Fit

S88Excellent

Estimated from fit model

Qwen 3.5 122B A10B needs ~90.8 GB VRAM. NVIDIA DGX Spark 128GB has 108.8 GB. With Q4_K_M quantization, expect ~7 tok/s.

Runtime: llama.cppCapacity: TightBandwidth: LowStack: StandardBottleneck: 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.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 90.8 GB, 6.6 tok/s, Tight fit

90.8 GB required108.8 GB available

83% VRAM used

Fit status

Tight fit

Decode

6.6 tok/s

TTFT

29399 ms

Safe context

131K

Memory

90.8 GB / 108.8 GB

Memory breakdown

Weights74.4 GB

KV Cache2.4 GB

Runtime0.9 GB

Headroom13.1 GB

See how fast it feels

See how fast it feelsQwen 3.5 122B A10B 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: 6.6 tok/s decode · 29.4s TTFT (warm) · 17 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	S	Tight fit	6.6 tok/s	16036 ms	131K
Coding	S	Tight fit	6.6 tok/s	29399 ms	131K
Agentic Coding	S	Tight fit	6.6 tok/s	42763 ms	131K
Reasoning	S	Tight fit	6.6 tok/s	34745 ms	131K
RAG	S	Tight fit	6.6 tok/s	53453 ms	131K

Inference speed

Qwen 3.5 122B A10B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Qwen 3.5 122B A10B at Q4_K_M across popular GPUs and Apple Silicon, including multi-GPU rigs, using the fastest local runtime per device. Fastest is Mac Studio M3 Ultra 256GB at ~35 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.

GPU / Mac	Memory	Quant	Speed (tok/s)	Fits?
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	34.7	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	28.9	Offloads
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	27.4	Offloads
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	21.4	Offloads
2× RX 7900 XTX 24GB	48 GB	Q4_K_M	11.3	Too big
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	10.0	Too big
2× RTX 4090 24GB	48 GB	Q4_K_M	7.6	Too big
RTX 5090 32GB	32 GB	Q4_K_M	7.2	Too big
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	7.0	Too big
2× RTX 3090 24GB	48 GB	Q4_K_M	6.5	Too big
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	6.4	Too big
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	5.9	Too big
4× RTX 3060 12GB	48 GB	Q4_K_M	5.7	Too big
RTX 4090 24GB	24 GB	Q4_K_M	4.6	Too big
RX 7900 XTX 24GB	24 GB	Q4_K_M	4.2	Too big
RTX 3090 24GB	24 GB	Q4_K_M	4.0	Too big
RTX 4080 Super 16GB	16 GB	Q4_K_M	3.7	Too big
RTX 4070 12GB	12 GB	Q4_K_M	2.3	Too big
RTX 3060 12GB	12 GB	Q4_K_M	2.0	Too big
RTX 4060 8GB	8 GB	Q4_K_M	2.0	Too big

Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.

Quantization options

How Qwen 3.5 122B A10B (122B params) fits at each quantization level on NVIDIA DGX Spark 128GB (92.2 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	47.6 GB	Low	S90
Q3_K_S	3	59.8 GB	Low	S90
NVFP4	4	68.3 GB	Medium	S90
Q4_K_MBest for your GPU	4	74.4 GB	Medium	S90
Q5_K_M	5	87.8 GB	High	F0
Q6_K	6	100.0 GB	High	F0
Q8_0	8	130.5 GB	Very High	F0
F16	16	250.1 GB	Maximum	F0

Get started

Copy-paste commands to run Qwen 3.5 122B A10B on your machine.

Run

lms load Qwen3.5-122B-A10B-Instruct && lms server start

Your hardware

More models your NVIDIA DGX Spark 128GB can run

Model	Params	Grade	Decode	Capabilities
Devstral 2 123B Instruct	123B	S	2.4 tok/s

Frequently asked questions

Can NVIDIA DGX Spark 128GB run Qwen 3.5 122B A10B?

Yes, NVIDIA DGX Spark 128GB can run Qwen 3.5 122B A10B with a S grade (Tight fit). Expected decode speed: 6.6 tok/s.

How much VRAM does Qwen 3.5 122B A10B need?

Qwen 3.5 122B A10B (122B parameters) requires approximately 90.8 GB of memory with Q4_K_M quantization.

What is the best quantization for Qwen 3.5 122B A10B?

The recommended quantization for Qwen 3.5 122B A10B is Q4_K_M, which balances quality and memory efficiency.

What speed will Qwen 3.5 122B A10B run at on NVIDIA DGX Spark 128GB?

On NVIDIA DGX Spark 128GB, Qwen 3.5 122B A10B achieves approximately 6.6 tokens per second decode speed with a time-to-first-token of 29399ms using Q4_K_M quantization.

Can NVIDIA DGX Spark 128GB run Qwen 3.5 122B A10B for coding?

For coding workloads, Qwen 3.5 122B A10B on NVIDIA DGX Spark 128GB receives a S grade with 6.6 tok/s and 131K context.

What context window can Qwen 3.5 122B A10B use on NVIDIA DGX Spark 128GB?

On NVIDIA DGX Spark 128GB, Qwen 3.5 122B A10B can safely use up to 131K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.

What should I upgrade first if Qwen 3.5 122B A10B 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 3.5 122B A10B?

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 3.5 122B A10B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/qwen-3.5-122b-a10b-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: