Is unified memory on Mac Studio M2 Ultra 128GB as fast as VRAM for Qwen 3.5 122B A10B?

Not always. Mac Studio M2 Ultra 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 3.5 122B A10B run on Mac Studio M2 Ultra 128GB?

Q: What should I upgrade first if Qwen 3.5 122B A10B feels slow on Mac Studio M2 Ultra 128GB?

Buy headroom, not only minimum fit. A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.

YES — With Offload

S93Excellent

Estimated from fit model

Qwen 3.5 122B A10B needs ~91.6 GB VRAM. Mac Studio M2 Ultra 128GB has 92.2 GB. With Q4_K_M quantization, expect ~29 tok/s.

Runtime: llama.cppCapacity: OffloadBandwidth: HighStack: StandardBottleneck: 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.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 91.6 GB, 28.9 tok/s, Runs with offload

91.6 GB required92.2 GB available

99% VRAM used

Fit status

Runs with offload

Decode

28.9 tok/s

TTFT

6696 ms

Safe context

20K

Memory

91.6 GB / 92.2 GB

Memory breakdown

Weights74.4 GB

KV Cache2.4 GB

Runtime0.9 GB

Headroom13.8 GB

See how fast it feels

See how fast it feelsQwen 3.5 122B A10B on Mac Studio M2 Ultra 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: 28.9 tok/s decode · 6.7s TTFT (warm) · 72 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

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

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 with offload	28.9 tok/s	3652 ms	20K
Coding	S	Runs with offload	28.9 tok/s	6696 ms	20K
Agentic Coding	S	Runs with offload (needs ~1.5 GB host RAM)	27.7 tok/s	10182 ms	20K
Reasoning	S	Runs with offload	28.9 tok/s	7913 ms	20K
RAG	S	Runs with offload (needs ~1.5 GB host RAM)	27.7 tok/s	12728 ms

Quantization options

How Qwen 3.5 122B A10B (122B params) fits at each quantization level on Mac Studio M2 Ultra 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

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 Mac Studio M2 Ultra 128GB can run

Model	Params	Grade	Decode	Capabilities
Devstral 2 123B Instruct	123B	S	6.3 tok/s

Frequently asked questions

Can Mac Studio M2 Ultra 128GB run Qwen 3.5 122B A10B?

Yes, Mac Studio M2 Ultra 128GB can run Qwen 3.5 122B A10B with a S grade (Runs with offload). Expected decode speed: 28.9 tok/s.

How much VRAM does Qwen 3.5 122B A10B need?

Qwen 3.5 122B A10B (122B parameters) requires approximately 91.6 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 Mac Studio M2 Ultra 128GB?

On Mac Studio M2 Ultra 128GB, Qwen 3.5 122B A10B achieves approximately 28.9 tokens per second decode speed with a time-to-first-token of 6696ms using Q4_K_M quantization.

Can Mac Studio M2 Ultra 128GB run Qwen 3.5 122B A10B for coding?

For coding workloads, Qwen 3.5 122B A10B on Mac Studio M2 Ultra 128GB receives a S grade with 28.9 tok/s and 20K context.

What context window can Qwen 3.5 122B A10B use on Mac Studio M2 Ultra 128GB?

On Mac Studio M2 Ultra 128GB, Qwen 3.5 122B A10B can safely use up to 20K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.

See all results for Mac Studio M2 Ultra 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-m2-ultra-128gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: