Can Gemma 4 12B run on Mac Studio M2 Ultra 128GB?

YES — Runs Great

A78Great

Estimated from fit model

Gemma 4 12B needs ~27.9 GB VRAM. Mac Studio M2 Ultra 128GB has 92.2 GB. With Q4_K_M quantization, expect ~50 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) — 27.9 GB, 50.4 tok/s, Runs well

27.9 GB required92.2 GB available

30% VRAM used

Fit status

Runs well

Decode

50.4 tok/s

TTFT

3838 ms

Safe context

191K

Memory

27.9 GB / 92.2 GB

Memory breakdown

Weights7.3 GB

KV Cache5.9 GB

Runtime0.9 GB

Headroom13.8 GB

See how fast it feels

See how fast it feelsGemma 4 12B 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: 50.4 tok/s decode · 3.8s TTFT (warm) · 126 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	A	Runs well	50.4 tok/s	2094 ms	191K
Coding	A	Runs well	50.4 tok/s	3838 ms	191K
Agentic Coding	A	Runs well	50.4 tok/s	5583 ms	191K
Reasoning	A	Runs well	50.4 tok/s	4536 ms	191K
RAG	A	Runs well	50.4 tok/s	6978 ms	191K

Inference speed

Gemma 4 12B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Gemma 4 12B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~168 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	168.0	Fits
RTX 4090 24GB	24 GB	Q4_K_M	109.9	Fits
RX 7900 XTX 24GB	24 GB	Q4_K_M	99.1	Fits
RTX 3090 24GB	24 GB	Q4_K_M	94.0	Fits
RTX 4080 Super 16GB	16 GB	Q4_K_M	87.6	Offloads
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	60.5	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	50.4	Fits
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	47.8	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	43.4	Fits
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	34.4	Fits
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	32.9	Fits
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	31.6	Fits
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	26.5	Fits
RTX 4070 12GB	12 GB	Q4_K_M	23.5	Too big
RTX 3060 12GB	12 GB	Q4_K_M	14.8	Too big
RTX 4060 8GB	8 GB	Q4_K_M	5.5	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 Gemma 4 12B (12B params) fits at each quantization level on Mac Studio M2 Ultra 128GB (92.2 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	4.7 GB	Low	A71
Q3_K_S	3	5.9 GB	Low	A71
NVFP4	4	6.7 GB	Medium	A71
Q4_K_M	4	7.3 GB	Medium	A71
Q5_K_M	5	8.6 GB	High	A71
Q6_K	6	9.8 GB	High	A71
Q8_0	8	12.8 GB	Very High	A71
F16Best for your GPU	16	24.6 GB	Maximum	A73

Get started

Copy-paste commands to run Gemma 4 12B on your machine.

Run

lms load gemma-4-12B-it && lms server start

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
Qwen3-Coder 30B A3B Instruct	30.5B	S	70.2 tok/s
Qwen 3.5 27B	27B	S	30.4 tok/s
Qwen 3.6 27B	27B	S	23.1 tok/s
Qwen 3.5 122B A10B	122B	S	28.9 tok/s

Frequently asked questions

Can Mac Studio M2 Ultra 128GB run Gemma 4 12B?

Yes, Mac Studio M2 Ultra 128GB can run Gemma 4 12B with a A grade (Runs well). Expected decode speed: 50.4 tok/s.

How much VRAM does Gemma 4 12B need?

Gemma 4 12B (12B parameters) requires approximately 27.9 GB of memory with Q4_K_M quantization.

What is the best quantization for Gemma 4 12B?

The recommended quantization for Gemma 4 12B is Q4_K_M, which balances quality and memory efficiency.

What speed will Gemma 4 12B run at on Mac Studio M2 Ultra 128GB?

On Mac Studio M2 Ultra 128GB, Gemma 4 12B achieves approximately 50.4 tokens per second decode speed with a time-to-first-token of 3838ms using Q4_K_M quantization.

Can Mac Studio M2 Ultra 128GB run Gemma 4 12B for coding?

For coding workloads, Gemma 4 12B on Mac Studio M2 Ultra 128GB receives a A grade with 50.4 tok/s and 191K context.

What context window can Gemma 4 12B use on Mac Studio M2 Ultra 128GB?

On Mac Studio M2 Ultra 128GB, Gemma 4 12B can safely use up to 191K tokens of context. The model's official context limit is 262K, but available memory constrains the safe maximum.

Is unified memory on Mac Studio M2 Ultra 128GB as fast as VRAM for Gemma 4 12B?

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 Gemma 4 12B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/gemma-4-12b-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: