Can Codestral 21B Pruned i1 run on MacBook Pro M3 Max 128GB?

YES — Runs Great

C43Usable

Estimated from fit model

Codestral 21B Pruned i1 needs ~30.0 GB VRAM. MacBook Pro M3 Max 128GB has 92.2 GB. With Q4_K_M quantization, expect ~19 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) — 30.0 GB, 18.7 tok/s, Runs well

30.0 GB required92.2 GB available

33% VRAM used

Fit status

Runs well

Decode

18.7 tok/s

TTFT

10333 ms

Safe context

420K

Memory

30.0 GB / 92.2 GB

Memory breakdown

Weights12.8 GB

KV Cache2.5 GB

Runtime0.9 GB

Headroom13.8 GB

See how fast it feels

See how fast it feelsCodestral 21B Pruned i1 on MacBook Pro M3 Max 128GB
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: 18.7 tok/s decode · 10.3s TTFT (warm) · 47 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	18.7 tok/s	5636 ms	420K
Coding	C	Runs well	18.7 tok/s	10333 ms	420K
Agentic Coding	C	Runs well	18.7 tok/s	15030 ms	420K
Reasoning	C	Runs well	18.7 tok/s	12212 ms	420K
RAG	C	Runs well	18.7 tok/s	18788 ms	420K

Quantization options

How Codestral 21B Pruned i1 (21B params) fits at each quantization level on MacBook Pro M3 Max 128GB (92.2 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	8.2 GB	Low	D39
Q3_K_S	3	10.3 GB	Low	D39
NVFP4	4	11.8 GB	Medium	D39
Q4_K_M	4	12.8 GB	Medium	D39
Q5_K_M	5	15.1 GB	High	D40
Q6_K	6	17.2 GB	High	D40
Q8_0	8	22.5 GB	Very High	C41
F16Best for your GPU	16	43.1 GB	Maximum	C45

Get started

Copy-paste commands to run Codestral 21B Pruned i1 on your machine.

Run

lms load hf-mradermacher--codestral-21b-pruned-i1-gguf && lms server start

升级选项

能流畅运行 Codestral 21B Pruned i1 的硬件

Mac Studio M3 Ultra 256GB经济之选

256 GB Unified (+128)819 GB/s (+419)

Raises estimated decode speed by about 133%.43.5 tok/s 解码

Raises estimated decode speed by about 133%.

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

~$6,999 MSRP

AMD Instinct MI350X 288GB最佳性价比

288 GB VRAM (+160)8000 GB/s (+7600)

Raises estimated decode speed by about 1472%.294 tok/s 解码

Raises estimated decode speed by about 1472%.

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

~$8,000 MSRP

Frequently asked questions

Can MacBook Pro M3 Max 128GB run Codestral 21B Pruned i1?

Yes, MacBook Pro M3 Max 128GB can run Codestral 21B Pruned i1 with a C grade (Runs well). Expected decode speed: 18.7 tok/s.

How much VRAM does Codestral 21B Pruned i1 need?

Codestral 21B Pruned i1 (21B parameters) requires approximately 30.0 GB of memory with Q4_K_M quantization.

What is the best quantization for Codestral 21B Pruned i1?

The recommended quantization for Codestral 21B Pruned i1 is Q4_K_M, which balances quality and memory efficiency.

What speed will Codestral 21B Pruned i1 run at on MacBook Pro M3 Max 128GB?

On MacBook Pro M3 Max 128GB, Codestral 21B Pruned i1 achieves approximately 18.7 tokens per second decode speed with a time-to-first-token of 10333ms using Q4_K_M quantization.

Can MacBook Pro M3 Max 128GB run Codestral 21B Pruned i1 for coding?

For coding workloads, Codestral 21B Pruned i1 on MacBook Pro M3 Max 128GB receives a C grade with 18.7 tok/s and 420K context.

What context window can Codestral 21B Pruned i1 use on MacBook Pro M3 Max 128GB?

On MacBook Pro M3 Max 128GB, Codestral 21B Pruned i1 can safely use up to 420K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.

Is unified memory on MacBook Pro M3 Max 128GB as fast as VRAM for Codestral 21B Pruned i1?

Not always. MacBook Pro M3 Max 128GB 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 M3 Max 128GB See all hardware for Codestral 21B Pruned 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-21b-pruned-i1-gguf-on-m3-max-128gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: