Can GPT-OSS 120B run on Mac Studio M1 Ultra 128GB?

YES — With Offload

S86Excellent

Estimated from fit model

GPT-OSS 120B needs ~91.0 GB VRAM. Mac Studio M1 Ultra 128GB has 92.2 GB. With Q4_K_M quantization, expect ~7 tok/s.

Runtime: llama.cppCapacity: OffloadBandwidth: 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) — 91.0 GB, 6.7 tok/s, Runs with offload

91.0 GB required92.2 GB available

99% VRAM used

Fit status

Runs with offload

Decode

6.7 tok/s

TTFT

28876 ms

Safe context

20K

Memory

91.0 GB / 92.2 GB

Memory breakdown

Weights71.4 GB

KV Cache4.9 GB

Runtime0.9 GB

Headroom13.8 GB

See how fast it feels

See how fast it feelsGPT-OSS 120B on Mac Studio M1 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: 6.7 tok/s decode · 28.9s TTFT (warm) · 17 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	Runs with offload	6.7 tok/s	15751 ms	20K
Coding	S	Runs with offload	6.7 tok/s	28876 ms	20K
Agentic Coding	S	Runs with offload (needs ~2.8 GB host RAM)	6.2 tok/s	45358 ms	20K
Reasoning	S	Runs with offload	6.7 tok/s	34126 ms	20K
RAG	S	Runs with offload (needs ~2.8 GB host RAM)	6.2 tok/s	56698 ms	20K

Quantization options

How GPT-OSS 120B (117B params) fits at each quantization level on Mac Studio M1 Ultra 128GB (92.2 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	45.6 GB	Low	S88
Q3_K_S	3	57.3 GB	Low	S88
NVFP4	4	65.5 GB	Medium	S88
Q4_K_MBest for your GPU	4	71.4 GB	Medium	S88
Q5_K_M	5	84.2 GB	High	F0
Q6_K	6	95.9 GB	High	F0
Q8_0	8	125.2 GB	Very High	F0
F16	16	239.8 GB	Maximum	F0

Get started

Copy-paste commands to run GPT-OSS 120B on your machine.

Run

ollama run gpt-oss:120b

Your hardware

More models your Mac Studio M1 Ultra 128GB can run

Model	Params	Grade	Decode
Devstral 2 123B Instruct	123B	S	6 tok/s
Qwen 3.5 122B A10B	122B	S	27.4 tok/s
Mistral Small 4 119B	119B	S	29.3 tok/s

Frequently asked questions

Can Mac Studio M1 Ultra 128GB run GPT-OSS 120B?

Yes, Mac Studio M1 Ultra 128GB can run GPT-OSS 120B with a S grade (Runs with offload). Expected decode speed: 6.7 tok/s.

How much VRAM does GPT-OSS 120B need?

GPT-OSS 120B (117B parameters) requires approximately 91.0 GB of memory with Q4_K_M quantization.

What is the best quantization for GPT-OSS 120B?

The recommended quantization for GPT-OSS 120B is Q4_K_M, which balances quality and memory efficiency.

What speed will GPT-OSS 120B run at on Mac Studio M1 Ultra 128GB?

On Mac Studio M1 Ultra 128GB, GPT-OSS 120B achieves approximately 6.7 tokens per second decode speed with a time-to-first-token of 28876ms using Q4_K_M quantization.

Can Mac Studio M1 Ultra 128GB run GPT-OSS 120B for coding?

For coding workloads, GPT-OSS 120B on Mac Studio M1 Ultra 128GB receives a S grade with 6.7 tok/s and 20K context.

What context window can GPT-OSS 120B use on Mac Studio M1 Ultra 128GB?

On Mac Studio M1 Ultra 128GB, GPT-OSS 120B can safely use up to 20K tokens of context. The model's official context limit is 131K, but available memory constrains the safe maximum.

What should I upgrade first if GPT-OSS 120B feels slow on Mac Studio M1 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 M1 Ultra 128GB as fast as VRAM for GPT-OSS 120B?

Not always. Mac Studio M1 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 M1 Ultra 128GB See all hardware for GPT-OSS 120B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/gpt-oss-120b-on-m1-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: