Can Codestral 2 25.08 run on Mac Studio M3 Ultra 96GB?

YES — Runs Great

A82Great

Estimated from fit model

Codestral 2 25.08 needs ~27.1 GB VRAM. Mac Studio M3 Ultra 96GB has 69.1 GB. With Q4_K_M quantization, expect ~39 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) — 27.1 GB, 41.9 tok/s, Runs well

27.1 GB required69.1 GB available

39% VRAM used

Fit status

Runs well

Decode

41.9 tok/s

TTFT

4617 ms

Safe context

256K

Memory

27.1 GB / 69.1 GB

Memory breakdown

Weights13.4 GB

KV Cache2.4 GB

Runtime0.9 GB

Headroom10.4 GB

See how fast it feels

See how fast it feelsCodestral 2 25.08 on Mac Studio M3 Ultra 96GB
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: 41.9 tok/s decode · 4.6s TTFT (warm) · 105 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	39.0 tok/s	2707 ms	256K
Coding	A	Runs well	39.0 tok/s	4963 ms	256K
Agentic Coding	A	Runs well	39.0 tok/s	7219 ms	256K
Reasoning	A	Runs well	39.0 tok/s	5865 ms	256K
RAG	A	Runs well	39.0 tok/s	9023 ms	256K

Quantization options

How Codestral 2 25.08 (22B params) fits at each quantization level on Mac Studio M3 Ultra 96GB (69.1 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	8.6 GB	Low	A75
Q3_K_S	3	10.8 GB	Low	A75
NVFP4	4	12.3 GB	Medium	A76
Q4_K_M	4	13.4 GB	Medium	A76
Q5_K_M	5	15.8 GB	High	A76
Q6_K	6	18.0 GB	High	A77
Q8_0	8	23.5 GB	Very High	A78
F16Best for your GPU	16	45.1 GB	Maximum	A82

Get started

Copy-paste commands to run Codestral 2 25.08 on your machine.

Run

lms load codestral-2508 && lms server start

Your hardware

More models your Mac Studio M3 Ultra 96GB can run

Model	Params	Grade	Decode
Qwen3-Coder 30B A3B Instruct	30.5B	S	84.2 tok/s
Qwen 3.5 27B	27B	S	36.5 tok/s
Qwen 3.6 27B	27B	S	27.8 tok/s
Qwen 3.6 35B A3B	35B	S	70.8 tok/s
Qwen3-VL 30B A3B Instruct	30B	S	87.1 tok/s

Frequently asked questions

Can Mac Studio M3 Ultra 96GB run Codestral 2 25.08?

Yes, Mac Studio M3 Ultra 96GB can run Codestral 2 25.08 with a A grade (Runs well). Expected decode speed: 39.0 tok/s.

How much VRAM does Codestral 2 25.08 need?

Codestral 2 25.08 (22B parameters) requires approximately 27.1 GB of memory with Q4_K_M quantization.

What is the best quantization for Codestral 2 25.08?

The recommended quantization for Codestral 2 25.08 is Q4_K_M, which balances quality and memory efficiency.

What speed will Codestral 2 25.08 run at on Mac Studio M3 Ultra 96GB?

On Mac Studio M3 Ultra 96GB, Codestral 2 25.08 achieves approximately 39.0 tokens per second decode speed with a time-to-first-token of 4963ms using Q4_K_M quantization.

Can Mac Studio M3 Ultra 96GB run Codestral 2 25.08 for coding?

For coding workloads, Codestral 2 25.08 on Mac Studio M3 Ultra 96GB receives a A grade with 39.0 tok/s and 256K context.

What context window can Codestral 2 25.08 use on Mac Studio M3 Ultra 96GB?

On Mac Studio M3 Ultra 96GB, Codestral 2 25.08 can safely use up to 256K tokens of context. The model's official context limit is 256K, but available memory constrains the safe maximum.

Is unified memory on Mac Studio M3 Ultra 96GB as fast as VRAM for Codestral 2 25.08?

Not always. Mac Studio M3 Ultra 96GB 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 M3 Ultra 96GB See all hardware for Codestral 2 25.08

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/codestral-2-25.08-on-m3-ultra-96gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: