Can Codestral 22B v0.1 i1 run on MacBook Pro M4 Max 36GB?

YES — Runs Great

C52Usable

Estimated from fit model

Codestral 22B v0.1 i1 needs ~20.8 GB VRAM. MacBook Pro M4 Max 36GB has 25.9 GB. With Q4_K_M quantization, expect ~28 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: LowStack: 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) — 20.8 GB, 27.8 tok/s, Runs well

20.8 GB required25.9 GB available

80% VRAM used

Fit status

Runs well

Decode

27.8 tok/s

TTFT

6975 ms

Safe context

48K

Memory

20.8 GB / 25.9 GB

Memory breakdown

Weights13.4 GB

KV Cache2.6 GB

Runtime0.9 GB

Headroom3.9 GB

See how fast it feels

See how fast it feelsCodestral 22B v0.1 i1 on MacBook Pro M4 Max 36GB
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: 27.8 tok/s decode · 7.0s TTFT (warm) · 69 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	C	Runs well	27.8 tok/s	3805 ms	48K
Coding	C	Runs well	27.8 tok/s	6975 ms	48K
Agentic Coding	C	Tight fit	27.8 tok/s	10146 ms	48K
Reasoning	C	Runs well	27.8 tok/s	8244 ms	48K
RAG	C	Tight fit	27.8 tok/s	12683 ms	48K

Quantization options

How Codestral 22B v0.1 i1 (22B params) fits at each quantization level on MacBook Pro M4 Max 36GB (25.9 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	8.6 GB	Low	C47
Q3_K_S	3	10.8 GB	Low	C48
NVFP4	4	12.3 GB	Medium	C49
Q4_K_M	4	13.4 GB	Medium	C50
Q5_K_M	5	15.8 GB	High	C49
Q6_KBest for your GPU	6	18.0 GB	High	C49
Q8_0	8	23.5 GB	Very High	F0
F16	16	45.1 GB	Maximum	F0

Get started

Copy-paste commands to run Codestral 22B v0.1 i1 on your machine.

Run

lms load hf-mradermacher--codestral-22b-v0-1-i1-gguf && lms server start

升级选项

能流畅运行 Codestral 22B v0.1 i1 的硬件

RTX 5090 32GB经济之选

1792 GB/s (+1382)

Raises estimated decode speed by about 175%.76.5 tok/s 解码

Raises estimated decode speed by about 175%.

Adds memory headroom for longer context windows and future model growth.

~$1,999 MSRP

RTX PRO 4500 Blackwell 32GB最佳性价比

896 GB/s (+486)

Raises estimated decode speed by about 102%.56.1 tok/s 解码

Raises estimated decode speed by about 102%.

Adds memory headroom for longer context windows and future model growth.

~$2,499 MSRP

Frequently asked questions

Can MacBook Pro M4 Max 36GB run Codestral 22B v0.1 i1?

Yes, MacBook Pro M4 Max 36GB can run Codestral 22B v0.1 i1 with a C grade (Runs well). Expected decode speed: 27.8 tok/s.

How much VRAM does Codestral 22B v0.1 i1 need?

Codestral 22B v0.1 i1 (22B parameters) requires approximately 20.8 GB of memory with Q4_K_M quantization.

What is the best quantization for Codestral 22B v0.1 i1?

The recommended quantization for Codestral 22B v0.1 i1 is Q4_K_M, which balances quality and memory efficiency.

What speed will Codestral 22B v0.1 i1 run at on MacBook Pro M4 Max 36GB?

On MacBook Pro M4 Max 36GB, Codestral 22B v0.1 i1 achieves approximately 27.8 tokens per second decode speed with a time-to-first-token of 6975ms using Q4_K_M quantization.

Can MacBook Pro M4 Max 36GB run Codestral 22B v0.1 i1 for coding?

For coding workloads, Codestral 22B v0.1 i1 on MacBook Pro M4 Max 36GB receives a C grade with 27.8 tok/s and 48K context.

What context window can Codestral 22B v0.1 i1 use on MacBook Pro M4 Max 36GB?

On MacBook Pro M4 Max 36GB, Codestral 22B v0.1 i1 can safely use up to 48K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.

Is unified memory on MacBook Pro M4 Max 36GB as fast as VRAM for Codestral 22B v0.1 i1?

Not always. MacBook Pro M4 Max 36GB 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 Pro M4 Max 36GB See all hardware for Codestral 22B v0.1 i1

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/hf-mradermacher--codestral-22b-v0-1-i1-gguf-on-m4-max-36gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: