Can Qwen 3.5 27B run on Mac Studio M2 Ultra 128GB?

YES — Runs Great

S89Excellent

Estimated from fit model

Qwen 3.5 27B needs ~34.4 GB VRAM. Mac Studio M2 Ultra 128GB has 92.2 GB. With Q4_K_M quantization, expect ~30 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: 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) — 34.4 GB, 30.4 tok/s, Runs well

34.4 GB required92.2 GB available

37% VRAM used

Fit status

Runs well

Decode

30.4 tok/s

TTFT

6363 ms

Safe context

131K

Memory

34.4 GB / 92.2 GB

Memory breakdown

Weights16.5 GB

KV Cache3.2 GB

Runtime0.9 GB

Headroom13.8 GB

See how fast it feels

See how fast it feelsQwen 3.5 27B 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: 30.4 tok/s decode · 6.4s TTFT (warm) · 76 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	S	Runs well	30.4 tok/s	3471 ms	131K
Coding	S	Runs well	30.4 tok/s	6363 ms	131K
Agentic Coding	S	Runs well	30.4 tok/s	9255 ms	131K
Reasoning	S	Runs well	30.4 tok/s	7520 ms	131K
RAG	S	Runs well	30.4 tok/s	11569 ms	131K

Inference speed

Qwen 3.5 27B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Qwen 3.5 27B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~79 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?
RTX 5090 32GB	32 GB	Q4_K_M	78.7	Fits
RTX 4090 24GB	24 GB	Q4_K_M	50.2	Offloads
RX 7900 XTX 24GB	24 GB	Q4_K_M	45.3	Offloads
RTX 3090 24GB	24 GB	Q4_K_M	43.0	Offloads
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	36.5	Fits
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	36.1	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	36.1	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	30.4	Fits
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	28.9	Fits
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	22.7	Fits
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	15.7	Fits
RTX 4080 Super 16GB	16 GB	Q4_K_M	14.7	Too big
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	14.4	Fits
RTX 4070 12GB	12 GB	Q4_K_M	5.2	Too big
RTX 3060 12GB	12 GB	Q4_K_M	3.2	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 27B (27B params) fits at each quantization level on Mac Studio M2 Ultra 128GB (92.2 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	10.5 GB	Low	A82
Q3_K_S	3	13.2 GB	Low	A83
NVFP4	4	15.1 GB	Medium	A83
Q4_K_M	4	16.5 GB	Medium	A83
Q5_K_M	5	19.4 GB	High	A83
Q6_K	6	22.1 GB	High	A84
Q8_0	8	28.9 GB	Very High	A85
F16Best for your GPU	16	55.4 GB	Maximum	S90

Get started

Copy-paste commands to run Qwen 3.5 27B on your machine.

Run

ollama run qwen3.5:27b

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
Qwen3-Coder 30B A3B Instruct	30.5B	S	70.2 tok/s

Frequently asked questions

Can Mac Studio M2 Ultra 128GB run Qwen 3.5 27B?

Yes, Mac Studio M2 Ultra 128GB can run Qwen 3.5 27B with a S grade (Runs well). Expected decode speed: 30.4 tok/s.

How much VRAM does Qwen 3.5 27B need?

Qwen 3.5 27B (27B parameters) requires approximately 34.4 GB of memory with Q4_K_M quantization.

What is the best quantization for Qwen 3.5 27B?

The recommended quantization for Qwen 3.5 27B is Q4_K_M, which balances quality and memory efficiency.

What speed will Qwen 3.5 27B run at on Mac Studio M2 Ultra 128GB?

On Mac Studio M2 Ultra 128GB, Qwen 3.5 27B achieves approximately 30.4 tokens per second decode speed with a time-to-first-token of 6363ms using Q4_K_M quantization.

Can Mac Studio M2 Ultra 128GB run Qwen 3.5 27B for coding?

For coding workloads, Qwen 3.5 27B on Mac Studio M2 Ultra 128GB receives a S grade with 30.4 tok/s and 131K context.

What context window can Qwen 3.5 27B use on Mac Studio M2 Ultra 128GB?

On Mac Studio M2 Ultra 128GB, Qwen 3.5 27B can safely use up to 131K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.

Is unified memory on Mac Studio M2 Ultra 128GB as fast as VRAM for Qwen 3.5 27B?

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.

See all results for Mac Studio M2 Ultra 128GB See all hardware for Qwen 3.5 27B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/qwen-3.5-27b-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: