Can Codestral 2 25.08 run on MacBook Pro M4 Max 96GB?

YES — Runs Great

A81Great

○Estimated from fit model

Codestral 2 25.08 needs ~27.1 GB VRAM. MacBook Pro M4 Max 96GB has 69.1 GB. With Q4_K_M quantization, expect ~35 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: MediumStack: 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, 35.2 tok/s, Runs well

27.1 GB required69.1 GB available

39% VRAM used

Fit status

Runs well

Decode

35.2 tok/s

TTFT

5504 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 MacBook Pro M4 Max 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: 35.2 tok/s decode · 5.5s TTFT (warm) · 88 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	35.2 tok/s	3002 ms	256K
Coding	A	Runs well	35.2 tok/s	5504 ms	256K
Agentic Coding	A	Runs well	35.2 tok/s	8006 ms	256K
Reasoning	A	Runs well	35.2 tok/s	6505 ms	256K
RAG	A	Runs well	35.2 tok/s	10008 ms	256K

Quantization options

How Codestral 2 25.08 (22B params) fits at each quantization level on MacBook Pro M4 Max 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 MacBook Pro M4 Max 96GB can run

Model	Params	Grade	Decode
👁 Alibaba Qwen3-Coder 30B A3B Instruct	30.5B	S	52 tok/s
👁 Alibaba Qwen 3.5 27B	27B	S	36.1 tok/s
👁 Alibaba Qwen 3.6 27B	27B	S	27.4 tok/s
👁 Alibaba Qwen 3.6 35B A3B	35B	S	43.7 tok/s
👁 Alibaba Qwen3-VL 30B A3B Instruct	30B	S	53.8 tok/s

Frequently asked questions

See all results for MacBook Pro M4 Max 96GB See all hardware for Codestral 2 25.08

URL: https://willitrunai.com/can-run/codestral-2-25.08-on-m4-max-96gb

⇱ Codestral 2 25.08 on MacBook Pro M4 Max 96GB? YES