Can Codestral 2 25.08 run on Mac Studio M2 Ultra 64GB?

YES — Runs Great

A84Great

○Estimated from fit model

Codestral 2 25.08 needs ~23.7 GB VRAM. Mac Studio M2 Ultra 64GB has 46.1 GB. With Q4_K_M quantization, expect ~35 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) — 23.7 GB, 34.9 tok/s, Runs well

23.7 GB required46.1 GB available

51% VRAM used

Fit status

Runs well

Decode

34.9 tok/s

TTFT

5541 ms

Safe context

163K

Memory

23.7 GB / 46.1 GB

Memory breakdown

Weights13.4 GB

KV Cache2.4 GB

Runtime0.9 GB

Headroom6.9 GB

See how fast it feels

See how fast it feelsCodestral 2 25.08 on Mac Studio M2 Ultra 64GB
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: 34.9 tok/s decode · 5.5s TTFT (warm) · 87 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	34.9 tok/s	3022 ms	163K
Coding	A	Runs well	34.9 tok/s	5541 ms	163K
Agentic Coding	S	Runs well	34.9 tok/s	8060 ms	163K
Reasoning	A	Runs well	34.9 tok/s	6549 ms	163K
RAG	S	Runs well	34.9 tok/s	10075 ms	163K

Quantization options

How Codestral 2 25.08 (22B params) fits at each quantization level on Mac Studio M2 Ultra 64GB (46.1 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	8.6 GB	Low	A77
Q3_K_S	3	10.8 GB	Low	A78
NVFP4	4	12.3 GB	Medium	A78
Q4_K_M	4	13.4 GB	Medium	A78
Q5_K_M	5	15.8 GB	High	A79
Q6_K	6	18.0 GB	High	A80
Q8_0Best for your GPU	8	23.5 GB	Very High	A82
F16	16	45.1 GB	Maximum	F0

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 M2 Ultra 64GB can run

Model	Params	Grade	Decode
👁 Alibaba Qwen3-Coder 30B A3B Instruct	30.5B	S	70.2 tok/s
👁 Alibaba Qwen 3.5 27B	27B	S	30.4 tok/s
👁 Alibaba Qwen 3.6 27B	27B	S	23.1 tok/s
👁 Alibaba Qwen 3.6 35B A3B	35B	S	59 tok/s
👁 Alibaba Qwen3-VL 30B A3B Instruct	30B	S	72.6 tok/s

Frequently asked questions

See all results for Mac Studio M2 Ultra 64GB See all hardware for Codestral 2 25.08

URL: https://willitrunai.com/can-run/codestral-2-25.08-on-m2-ultra-64gb

⇱ Codestral 2 25.08 on Mac Studio M2 Ultra 64GB? YES