Can Mistral Small 4 119B run on Mac Studio M2 Ultra 128GB?

YES — With Offload

S91Excellent

Estimated from fit model

Mistral Small 4 119B needs ~92.7 GB VRAM. Mac Studio M2 Ultra 128GB has 92.2 GB. With Q4_K_M quantization, expect ~31 tok/s.

Runtime: llama.cppCapacity: OffloadBandwidth: 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) — 92.7 GB, 30.8 tok/s, Runs with offload (needs ~0.4 GB host RAM)

92.7 GB required92.2 GB available

101% VRAM needed

0.5 GB over capacity — needs offload or smaller quantization

Fit status

Runs with offload (needs ~0.4 GB host RAM)

Decode

30.8 tok/s

TTFT

6276 ms

Safe context

14K

Memory

92.7 GB / 92.2 GB

Memory breakdown

Weights72.6 GB

KV Cache5.4 GB

Runtime0.9 GB

Headroom13.8 GB

See how fast it feels

See how fast it feelsMistral Small 4 119B 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: 30.8 tok/s decode · 6.3s TTFT (warm) · 77 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

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

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	31.3 tok/s	3369 ms	14K
Coding	S	Runs with offload (needs ~0.4 GB host RAM)	30.8 tok/s	6276 ms	14K
Agentic Coding	A	Runs with offload (needs ~4.4 GB host RAM)	28.0 tok/s	10042 ms	14K
Reasoning	S	Runs with offload (needs ~0.4 GB host RAM)	30.8 tok/s	7417 ms	14K
RAG	A	Runs with offload (needs ~4.4 GB host RAM)	28.0 tok/s	12553 ms	14K

Quantization options

How Mistral Small 4 119B (119B params) fits at each quantization level on Mac Studio M2 Ultra 128GB (92.2 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	46.4 GB	Low	S88
Q3_K_S	3	58.3 GB	Low	S88
NVFP4	4	66.6 GB	Medium	S88
Q4_K_MBest for your GPU	4	72.6 GB	Medium	S88
Q5_K_M	5	85.7 GB	High	F0
Q6_K	6	97.6 GB	High	F0
Q8_0	8	127.3 GB	Very High	F0
F16	16	244.0 GB	Maximum	F0

Get started

Copy-paste commands to run Mistral Small 4 119B on your machine.

Run

lms load Mistral-Small-4-119B-2603 && lms server start

Your hardware

More models your Mac Studio M2 Ultra 128GB can run

Model	Params	Grade	Decode	Capabilities
Devstral 2 123B Instruct	123B	S	6.3 tok/s
Qwen 3.5 122B A10B	122B	S	28.9 tok/s

Frequently asked questions

Can Mac Studio M2 Ultra 128GB run Mistral Small 4 119B?

Yes, Mac Studio M2 Ultra 128GB can run Mistral Small 4 119B with a S grade (Runs with offload (needs ~0.4 GB host RAM)). Expected decode speed: 30.8 tok/s.

How much VRAM does Mistral Small 4 119B need?

Mistral Small 4 119B (119B parameters) requires approximately 92.7 GB of memory with Q4_K_M quantization.

What is the best quantization for Mistral Small 4 119B?

The recommended quantization for Mistral Small 4 119B is Q4_K_M, which balances quality and memory efficiency.

What speed will Mistral Small 4 119B run at on Mac Studio M2 Ultra 128GB?

On Mac Studio M2 Ultra 128GB, Mistral Small 4 119B achieves approximately 30.8 tokens per second decode speed with a time-to-first-token of 6276ms using Q4_K_M quantization.

Can Mac Studio M2 Ultra 128GB run Mistral Small 4 119B for coding?

For coding workloads, Mistral Small 4 119B on Mac Studio M2 Ultra 128GB receives a S grade with 30.8 tok/s and 14K context.

What context window can Mistral Small 4 119B use on Mac Studio M2 Ultra 128GB?

On Mac Studio M2 Ultra 128GB, Mistral Small 4 119B can safely use up to 14K tokens of context. The model's official context limit is 256K, but available memory constrains the safe maximum.

What should I upgrade first if Mistral Small 4 119B feels slow on Mac Studio M2 Ultra 128GB?

Buy headroom, not only minimum fit. A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.

Is unified memory on Mac Studio M2 Ultra 128GB as fast as VRAM for Mistral Small 4 119B?

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 Mistral Small 4 119B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/mistral-small-4-119b-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

This setup is broadly balanced for this model.

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.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	S	Runs with offload	31.3 tok/s	3369 ms	14K
Coding	S	Runs with offload (needs ~0.4 GB host RAM)	30.8 tok/s	6276 ms	14K
Agentic Coding	A	Runs with offload (needs ~4.4 GB host RAM)	28.0 tok/s	10042 ms	14K
Reasoning	S	Runs with offload (needs ~0.4 GB host RAM)	30.8 tok/s	7417 ms	14K
RAG	A	Runs with offload (needs ~4.4 GB host RAM)	28.0 tok/s	12553 ms	14K

Quantization options

How Mistral Small 4 119B (119B params) fits at each quantization level on Mac Studio M2 Ultra 128GB (92.2 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	46.4 GB	Low	S88
Q3_K_S	3	58.3 GB	Low	S88
NVFP4	4	66.6 GB	Medium	S88
Q4_K_MBest for your GPU	4	72.6 GB	Medium	S88
Q5_K_M	5	85.7 GB	High	F0
Q6_K	6	97.6 GB	High	F0
Q8_0	8	127.3 GB	Very High	F0
F16	16	244.0 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