Will It Run AI

Can Codestral 22B v0.1 run on MacBook Pro M4 Pro 48GB?

YES — Runs Great

C51Usable
Estimated — low-sample bucket· few comparable runs

Codestral 22B v0.1 needs ~22.1 GB VRAM. MacBook Pro M4 Pro 48GB has 34.6 GB. With Q4_K_M quantization, expect ~22 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: LowStack: StandardBottleneck: Balanced
Share:

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) — 22.1 GB, 21.9 tok/s, Runs well
22.1 GB required34.6 GB available
64% VRAM used

Fit status

Runs well

Decode

21.9 tok/s

TTFT

8828 ms

Safe context

93K

Memory

22.1 GB / 34.6 GB

Memory breakdown

Weights13.4 GB
KV Cache2.6 GB
Runtime0.9 GB
Headroom5.2 GB

See how fast it feels

See how fast it feelsCodestral 22B v0.1 on MacBook Pro M4 Pro 48GB
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: 21.9 tok/s decode · 8.8s TTFT (warm) · 55 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

WorkloadGradeFitDecodeTTFTContext
ChatCRuns well21.9 tok/s4815 ms93K
CodingCRuns well21.9 tok/s8828 ms93K
Agentic CodingCRuns well21.9 tok/s12841 ms93K
ReasoningCRuns well21.9 tok/s10433 ms93K
RAGCRuns well21.9 tok/s16051 ms93K

Quantization options

How Codestral 22B v0.1 (22B params) fits at each quantization level on MacBook Pro M4 Pro 48GB (34.6 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
8.6 GB
LowC45
Q3_K_S
3
10.8 GB
LowC46
NVFP4
4
12.3 GB
MediumC46
Q4_K_M
4
13.4 GB
MediumC47
Q5_K_M
5
15.8 GB
HighC48
Q6_K
6
18.0 GB
HighC49
Q8_0Best for your GPU
8
23.5 GB
Very HighC49
F16
16
45.1 GB
MaximumF0

Get started

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

Run

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

Opciones de mejora

Hardware que ejecuta bien Codestral 22B v0.1

NVIDIARTX PRO 5000 Blackwell 48GBOpción económica
1344 GB/s (+1071)
C
Sube la velocidad estimada de decodificación alrededor de un 284%.84.1 tok/s decodificación

Sube la velocidad estimada de decodificación alrededor de un 284%.

Añade margen de memoria para más contexto y para que el modelo envejezca mejor.

~$4,999 MSRP

NVIDIANVIDIA A100 40GBMejor relación calidad-precio
1555 GB/s (+1282)
C
Sube la velocidad estimada de decodificación alrededor de un 344%.97.3 tok/s decodificación

Sube la velocidad estimada de decodificación alrededor de un 344%.

~$10,000 MSRP

Frequently asked questions

Can MacBook Pro M4 Pro 48GB run Codestral 22B v0.1?

Yes, MacBook Pro M4 Pro 48GB can run Codestral 22B v0.1 with a C grade (Runs well). Expected decode speed: 21.9 tok/s.

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

Codestral 22B v0.1 (22B parameters) requires approximately 22.1 GB of memory with Q4_K_M quantization.

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

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

What speed will Codestral 22B v0.1 run at on MacBook Pro M4 Pro 48GB?

On MacBook Pro M4 Pro 48GB, Codestral 22B v0.1 achieves approximately 21.9 tokens per second decode speed with a time-to-first-token of 8828ms using Q4_K_M quantization.

Can MacBook Pro M4 Pro 48GB run Codestral 22B v0.1 for coding?

For coding workloads, Codestral 22B v0.1 on MacBook Pro M4 Pro 48GB receives a C grade with 21.9 tok/s and 93K context.

What context window can Codestral 22B v0.1 use on MacBook Pro M4 Pro 48GB?

On MacBook Pro M4 Pro 48GB, Codestral 22B v0.1 can safely use up to 93K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.

Is unified memory on MacBook Pro M4 Pro 48GB as fast as VRAM for Codestral 22B v0.1?

Not always. MacBook Pro M4 Pro 48GB 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 Pro 48GBSee all hardware for Codestral 22B v0.1
Embed this result▼

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

<iframe src="https://willitrunai.com/embed/hf-bartowski--codestral-22b-v0-1-gguf-on-m4-pro-48gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: