Can Codestral 21B Pruned i1 run on Mac mini M4 64GB?

YES — Runs Great

C45Usable

▲Estimated — low-sample bucket· few comparable runs

Codestral 21B Pruned i1 needs ~23.1 GB VRAM. Mac mini M4 64GB has 46.1 GB. With Q4_K_M quantization, expect ~9 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: Very lowStack: StandardBottleneck: Memory bandwidth

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) — 23.1 GB, 9.1 tok/s, Runs well

23.1 GB required46.1 GB available

50% VRAM used

Fit status

Runs well

Decode

9.1 tok/s

TTFT

21262 ms

Safe context

166K

Memory

23.1 GB / 46.1 GB

Memory breakdown

Weights12.8 GB

KV Cache2.5 GB

Runtime0.9 GB

Headroom6.9 GB

See how fast it feels

See how fast it feelsCodestral 21B Pruned i1 on Mac mini M4 64GB
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: 9.1 tok/s decode · 21.3s TTFT (warm) · 23 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	9.1 tok/s	11598 ms	166K
Coding	C	Runs well	9.1 tok/s	21262 ms	166K
Agentic Coding	C	Runs well	9.1 tok/s	30927 ms	166K
Reasoning	C	Runs well	9.1 tok/s	25128 ms	166K
RAG	C	Runs well	9.1 tok/s	38658 ms	166K

Quantization options

How Codestral 21B Pruned i1 (21B params) fits at each quantization level on Mac mini M4 64GB (46.1 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	8.2 GB	Low	C42
Q3_K_S	3	10.3 GB	Low	C43
NVFP4	4	11.8 GB	Medium	C43
Q4_K_M	4	12.8 GB	Medium	C44
Q5_K_M	5	15.1 GB	High	C44
Q6_K	6	17.2 GB	High	C45
Q8_0Best for your GPU	8	22.5 GB	Very High	C47
F16	16	43.1 GB	Maximum	F0