Can Qwen 3.6 35B A3B run on Mac Studio M3 Ultra 96GB?

YES — Runs Great

S95Excellent

Estimated from fit model

Qwen 3.6 35B A3B needs ~37.6 GB VRAM. Mac Studio M3 Ultra 96GB has 69.1 GB. With Q4_K_M quantization, expect ~71 tok/s.

Runtime: TransformersCapacity: 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) — 37.6 GB, 70.8 tok/s, Runs well

37.6 GB required69.1 GB available

54% VRAM used

Fit status

Runs well

Decode

70.8 tok/s

TTFT

2735 ms

Safe context

139K

Memory

37.6 GB / 69.1 GB

Memory breakdown

Weights21.3 GB

KV Cache4.1 GB

Runtime1.8 GB

Headroom10.4 GB

See how fast it feels

See how fast it feelsQwen 3.6 35B A3B on Mac Studio M3 Ultra 96GB
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: 70.8 tok/s decode · 2.7s TTFT (warm) · 177 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	70.8 tok/s	1492 ms	139K
Coding	S	Runs well	70.8 tok/s	2735 ms	139K
Agentic Coding	S	Runs well	70.8 tok/s	3979 ms	139K
Reasoning	S	Runs well	70.8 tok/s	3233 ms	139K
RAG	S	Runs well	70.8 tok/s	4974 ms	139K

Quantization options

How Qwen 3.6 35B A3B (35B params) fits at each quantization level on Mac Studio M3 Ultra 96GB (69.1 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	13.7 GB	Low	A84
Q3_K_S	3	17.2 GB	Low	A85
NVFP4	4	19.6 GB	Medium	S85
Q4_K_M	4	21.3 GB	Medium	S85
Q5_K_M	5	25.2 GB	High	S86
Q6_K	6	28.7 GB	High	S87
Q8_0Best for your GPU	8	37.5 GB	Very High	S90
F16	16	71.8 GB	Maximum	F0

Get started

Copy-paste commands to run Qwen 3.6 35B A3B on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
  --hf-repo "Qwen/Qwen3.6-35B-A3B" \
  --hf-file "Qwen3.6-35B-A3B-Q4_K_M.gguf" \
  -c 4096 -ngl 99

Frequently asked questions

Can Mac Studio M3 Ultra 96GB run Qwen 3.6 35B A3B?

Yes, Mac Studio M3 Ultra 96GB can run Qwen 3.6 35B A3B with a S grade (Runs well). Expected decode speed: 70.8 tok/s.

How much VRAM does Qwen 3.6 35B A3B need?

Qwen 3.6 35B A3B (35B parameters) requires approximately 37.6 GB of memory with Q4_K_M quantization.

What is the best quantization for Qwen 3.6 35B A3B?

The recommended quantization for Qwen 3.6 35B A3B is Q4_K_M, which balances quality and memory efficiency.

What speed will Qwen 3.6 35B A3B run at on Mac Studio M3 Ultra 96GB?

On Mac Studio M3 Ultra 96GB, Qwen 3.6 35B A3B achieves approximately 70.8 tokens per second decode speed with a time-to-first-token of 2735ms using Q4_K_M quantization.

Can Mac Studio M3 Ultra 96GB run Qwen 3.6 35B A3B for coding?

For coding workloads, Qwen 3.6 35B A3B on Mac Studio M3 Ultra 96GB receives a S grade with 70.8 tok/s and 139K context.

What context window can Qwen 3.6 35B A3B use on Mac Studio M3 Ultra 96GB?

On Mac Studio M3 Ultra 96GB, Qwen 3.6 35B A3B can safely use up to 139K tokens of context. The model's official context limit is 262K, but available memory constrains the safe maximum.

Is unified memory on Mac Studio M3 Ultra 96GB as fast as VRAM for Qwen 3.6 35B A3B?

Not always. Mac Studio M3 Ultra 96GB 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 M3 Ultra 96GB See all hardware for Qwen 3.6 35B A3B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/qwen-3.6-35b-a3b-on-m3-ultra-96gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: