Can LFM2 24B run on Mac Studio M1 Ultra 128GB?

YES — Runs Great

A79Great

Estimated from fit model

LFM2 24B needs ~31.8 GB VRAM. Mac Studio M1 Ultra 128GB has 92.2 GB. With Q4_K_M quantization, expect ~32 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) — 31.8 GB, 32.3 tok/s, Runs well

31.8 GB required92.2 GB available

34% VRAM used

Fit status

Runs well

Decode

32.3 tok/s

TTFT

5992 ms

Safe context

131K

Memory

31.8 GB / 92.2 GB

Memory breakdown

Weights14.6 GB

KV Cache2.4 GB

Runtime0.9 GB

Headroom13.8 GB

See how fast it feels

See how fast it feelsLFM2 24B 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: 32.3 tok/s decode · 6.0s TTFT (warm) · 81 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	32.3 tok/s	3268 ms	131K
Coding	A	Runs well	32.3 tok/s	5992 ms	131K
Agentic Coding	A	Runs well	32.3 tok/s	8716 ms	131K
Reasoning	A	Runs well	32.3 tok/s	7082 ms	131K
RAG	A	Runs well	32.3 tok/s	10895 ms	131K

Quantization options

How LFM2 24B (24B params) fits at each quantization level on Mac Studio M1 Ultra 128GB (92.2 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	9.4 GB	Low	A73
Q3_K_S	3	11.8 GB	Low	A73
NVFP4	4	13.4 GB	Medium	A73
Q4_K_M	4	14.6 GB	Medium	A73
Q5_K_M	5	17.3 GB	High	A74
Q6_K	6	19.7 GB	High	A74
Q8_0	8	25.7 GB	Very High	A75
F16Best for your GPU	16	49.2 GB	Maximum	A80

Get started

Copy-paste commands to run LFM2 24B on your machine.

Run

ollama run lfm2

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
Qwen3-Coder 30B A3B Instruct	30.5B	S	66.5 tok/s
Qwen 3.5 27B	27B	S	28.9 tok/s
Qwen 3.6 27B	27B	S	21.9 tok/s
Qwen 3.5 122B A10B	122B	S	27.4 tok/s

Frequently asked questions

Can Mac Studio M1 Ultra 128GB run LFM2 24B?

Yes, Mac Studio M1 Ultra 128GB can run LFM2 24B with a A grade (Runs well). Expected decode speed: 32.3 tok/s.

How much VRAM does LFM2 24B need?

LFM2 24B (24B parameters) requires approximately 31.8 GB of memory with Q4_K_M quantization.

What is the best quantization for LFM2 24B?

The recommended quantization for LFM2 24B is Q4_K_M, which balances quality and memory efficiency.

What speed will LFM2 24B run at on Mac Studio M1 Ultra 128GB?

On Mac Studio M1 Ultra 128GB, LFM2 24B achieves approximately 32.3 tokens per second decode speed with a time-to-first-token of 5992ms using Q4_K_M quantization.

Can Mac Studio M1 Ultra 128GB run LFM2 24B for coding?

For coding workloads, LFM2 24B on Mac Studio M1 Ultra 128GB receives a A grade with 32.3 tok/s and 131K context.

What context window can LFM2 24B use on Mac Studio M1 Ultra 128GB?

On Mac Studio M1 Ultra 128GB, LFM2 24B 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 M1 Ultra 128GB as fast as VRAM for LFM2 24B?

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 LFM2 24B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/lfm2-24b-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: