Can Codestral 2 25.08 run on MacBook Air M4 24GB?

BARELY — Tight on Memory

A70Great

Estimated — low-sample bucket· few comparable runs

Codestral 2 25.08 needs ~19.4 GB VRAM. MacBook Air M4 24GB has 17.3 GB. With Q4_K_M quantization, expect ~8 tok/s.

Runtime: llama.cppCapacity: OffloadBandwidth: Very lowStack: StandardBottleneck: Host offload

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) — 19.4 GB, 7.6 tok/s, Very compromised (needs ~1.4 GB host RAM)

19.4 GB required17.3 GB available

112% VRAM needed

2.1 GB over capacity — needs offload or smaller quantization

Fit status

Very compromised (needs ~1.4 GB host RAM)

Decode

7.6 tok/s

TTFT

25532 ms

Safe context

Memory

19.4 GB / 17.3 GB

Offload

10%

Memory breakdown

Weights13.4 GB

KV Cache2.4 GB

Runtime0.9 GB

Headroom2.6 GB

See how fast it feels

See how fast it feelsCodestral 2 25.08 on MacBook Air M4 24GB
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: 7.6 tok/s decode · 25.5s TTFT (warm) · 19 tok/s prefill

What limits this setup

It fits through host-memory offload, and offload is the main reason performance drops.

CPU or host-memory offload is active

About 10% of the working set spills out of accelerator memory, which usually hurts latency and sustained decode throughput.

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

Remove offload with more accelerator memory

Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.

Buy headroom, not only minimum fit

A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.

Increase host RAM if you keep offloading

This setup may need roughly 1.4 GB of extra host RAM just for the offloaded portion, before OS and other tools.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	A	Runs with offload (needs ~0.6 GB host RAM)	8.3 tok/s	12694 ms	4K
Coding	A	Very compromised (needs ~1.4 GB host RAM)	7.6 tok/s	25532 ms	4K
Agentic Coding	F	Too heavy	6.5 tok/s	43170 ms	4K
Reasoning	A	Very compromised (needs ~1.4 GB host RAM)	7.6 tok/s	30174 ms	4K
RAG	F	Too heavy	6.5 tok/s	53962 ms	4K

Quantization options

How Codestral 2 25.08 (22B params) fits at each quantization level on MacBook Air M4 24GB (17.3 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	8.6 GB	Low	S85
Q3_K_S	3	10.8 GB	Low	S85
NVFP4Best for your GPU	4	12.3 GB	Medium	A85
Q4_K_M	4	13.4 GB	Medium	F0
Q5_K_M	5	15.8 GB	High	F0
Q6_K	6	18.0 GB	High	F0
Q8_0	8	23.5 GB	Very High	F0
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 MacBook Air M4 24GB can run

Model	Params	Grade	Decode
Magistral Small 2507	24B	A	7.3 tok/s
Devstral Small 2 24B Instruct	24B	A	7.3 tok/s
Devstral Small 1.1	24B	B	7.3 tok/s

Frequently asked questions

Can MacBook Air M4 24GB run Codestral 2 25.08?

Yes, MacBook Air M4 24GB can run Codestral 2 25.08 with a A grade (Very compromised (needs ~1.4 GB host RAM)). Expected decode speed: 7.6 tok/s.

How much VRAM does Codestral 2 25.08 need?

Codestral 2 25.08 (22B parameters) requires approximately 19.4 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 MacBook Air M4 24GB?

On MacBook Air M4 24GB, Codestral 2 25.08 achieves approximately 7.6 tokens per second decode speed with a time-to-first-token of 25532ms using Q4_K_M quantization.

Can MacBook Air M4 24GB run Codestral 2 25.08 for coding?

For coding workloads, Codestral 2 25.08 on MacBook Air M4 24GB receives a A grade with 7.6 tok/s and 4K context.

What context window can Codestral 2 25.08 use on MacBook Air M4 24GB?

On MacBook Air M4 24GB, Codestral 2 25.08 can safely use up to 4K tokens of context. The model's official context limit is 256K, but available memory constrains the safe maximum.

What should I upgrade first if Codestral 2 25.08 feels slow on MacBook Air M4 24GB?

Remove offload with more accelerator memory. Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.

Is unified memory on MacBook Air M4 24GB as fast as VRAM for Codestral 2 25.08?

Not always. MacBook Air M4 24GB 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 MacBook Air M4 24GB 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-m4-air-24gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: