Can Codestral 21B Pruned i1 run on MacBook Pro M4 Max 36GB?

YES — Runs Great

C53Usable

○Estimated from fit model

Codestral 21B Pruned i1 needs ~20.1 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) — 20.1 GB, 28.0 tok/s, Runs well

20.1 GB required25.9 GB available

78% VRAM used

Fit status

Runs well

Decode

28.0 tok/s

TTFT

6905 ms

Safe context

54K

Memory

20.1 GB / 25.9 GB

Memory breakdown

Weights12.8 GB

KV Cache2.5 GB

Runtime0.9 GB

Headroom3.9 GB

See how fast it feels

See how fast it feelsCodestral 21B Pruned 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: 28.0 tok/s decode · 6.9s TTFT (warm) · 70 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	28.0 tok/s	3766 ms	54K
Coding	C	Runs well	28.0 tok/s	6905 ms	54K
Agentic Coding	C	Tight fit	28.0 tok/s	10044 ms	54K
Reasoning	C	Runs well	28.0 tok/s	8160 ms	54K
RAG	C	Tight fit	28.0 tok/s	12554 ms	54K

Quantization options

How Codestral 21B Pruned i1 (21B params) fits at each quantization level on MacBook Pro M4 Max 36GB (25.9 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	8.2 GB	Low	C46
Q3_K_S	3	10.3 GB	Low	C48
NVFP4	4	11.8 GB	Medium	C49
Q4_K_M	4	12.8 GB	Medium	C49
Q5_K_M	5	15.1 GB	High	C49
Q6_KBest for your GPU	6	17.2 GB	High	C49
Q8_0	8	22.5 GB	Very High	F0
F16	16	43.1 GB	Maximum	F0

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

Upgrade options

Hardware that runs Codestral 21B Pruned i1 well

👁 NVIDIA
RTX 5090 32GBBudget pick

1792 GB/s (+1382)

Raises estimated decode speed by about 196%.82.8 tok/s decode

Raises estimated decode speed by about 196%.

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

~$1,999 MSRP

👁 NVIDIA
RTX PRO 4500 Blackwell 32GBBest value

896 GB/s (+486)

Raises estimated decode speed by about 110%.58.8 tok/s decode

Raises estimated decode speed by about 110%.