Can Command A 111B run on Mac Studio M2 Ultra 128GB?

YES — Tight Fit

S86Excellent

Estimated from fit model

Command A 111B needs ~86.3 GB VRAM. Mac Studio M2 Ultra 128GB has 92.2 GB. With Q4_K_M quantization, expect ~8 tok/s.

Runtime: llama.cppCapacity: TightBandwidth: HighStack: 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) — 86.3 GB, 7.5 tok/s, Tight fit

86.3 GB required92.2 GB available

94% VRAM used

Fit status

Tight fit

Decode

7.5 tok/s

TTFT

25879 ms

Safe context

40K

Memory

86.3 GB / 92.2 GB

Memory breakdown

Weights67.7 GB

KV Cache3.9 GB

Runtime0.9 GB

Headroom13.8 GB

See how fast it feels

See how fast it feelsCommand A 111B 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: 7.5 tok/s decode · 25.9s TTFT (warm) · 19 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	Tight fit	7.5 tok/s	14116 ms	40K
Coding	S	Tight fit	7.5 tok/s	25879 ms	40K
Agentic Coding	S	Runs with offload	7.5 tok/s	37642 ms	40K
Reasoning	S	Tight fit	7.5 tok/s	30584 ms	40K
RAG	S	Runs with offload	7.5 tok/s	47053 ms	40K

Quantization options

How Command A 111B (111B params) fits at each quantization level on Mac Studio M2 Ultra 128GB (92.2 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	43.3 GB	Low	S87
Q3_K_S	3	54.4 GB	Low	S88
NVFP4	4	62.2 GB	Medium	S88
Q4_K_MBest for your GPU	4	67.7 GB	Medium	S88
Q5_K_M	5	79.9 GB	High	F0
Q6_K	6	91.0 GB	High	F0
Q8_0	8	118.8 GB	Very High	F0
F16	16	227.6 GB	Maximum	F0

Get started

Copy-paste commands to run Command A 111B on your machine.

Run

ollama run command-a

Your hardware

More models your Mac Studio M2 Ultra 128GB can run

Model	Params	Grade	Decode
Devstral 2 123B Instruct	123B	S	6.3 tok/s
Qwen 3.5 122B A10B	122B	S	28.9 tok/s
Mistral Small 4 119B	119B	S	30.8 tok/s
GPT-OSS 120B	117B	S	7.1 tok/s

Frequently asked questions

Can Mac Studio M2 Ultra 128GB run Command A 111B?

Yes, Mac Studio M2 Ultra 128GB can run Command A 111B with a S grade (Tight fit). Expected decode speed: 7.5 tok/s.

How much VRAM does Command A 111B need?

Command A 111B (111B parameters) requires approximately 86.3 GB of memory with Q4_K_M quantization.

What is the best quantization for Command A 111B?

The recommended quantization for Command A 111B is Q4_K_M, which balances quality and memory efficiency.

What speed will Command A 111B run at on Mac Studio M2 Ultra 128GB?

On Mac Studio M2 Ultra 128GB, Command A 111B achieves approximately 7.5 tokens per second decode speed with a time-to-first-token of 25879ms using Q4_K_M quantization.

Can Mac Studio M2 Ultra 128GB run Command A 111B for coding?

For coding workloads, Command A 111B on Mac Studio M2 Ultra 128GB receives a S grade with 7.5 tok/s and 40K context.

What context window can Command A 111B use on Mac Studio M2 Ultra 128GB?

On Mac Studio M2 Ultra 128GB, Command A 111B can safely use up to 40K tokens of context. The model's official context limit is 262K, but available memory constrains the safe maximum.

What should I upgrade first if Command A 111B feels slow on Mac Studio M2 Ultra 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 Mac Studio M2 Ultra 128GB as fast as VRAM for Command A 111B?

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 Command A 111B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/command-a-111b-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:

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.

Workload

Grade

Fit

Decode

TTFT

Context

Chat

Tight fit

7.5 tok/s

14116 ms

40K

Coding

Tight fit

7.5 tok/s

25879 ms

40K

Agentic Coding

Runs with offload

7.5 tok/s

37642 ms

40K

Reasoning

Tight fit

7.5 tok/s

30584 ms

40K

RAG

Runs with offload

7.5 tok/s

47053 ms

40K

Quantization options

How Command A 111B (111B params) fits at each quantization level on Mac Studio M2 Ultra 128GB (92.2 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	43.3 GB	Low	S87
Q3_K_S	3	54.4 GB	Low	S88
NVFP4	4	62.2 GB	Medium	S88
Q4_K_MBest for your GPU	4	67.7 GB	Medium	S88
Q5_K_M	5	79.9 GB	High	F0
Q6_K	6	91.0 GB	High	F0
Q8_0	8	118.8 GB	Very High	F0
F16	16	227.6 GB	Maximum	F0

Model

Params

Grade

Decode

Capabilities

Devstral 2 123B Instruct

123B

6.3 tok/s

Qwen 3.5 122B A10B

122B

28.9 tok/s

Mistral Small 4 119B

119B

30.8 tok/s

GPT-OSS 120B

117B

7.1 tok/s