Can Codestral 21B Pruned i1 run on Mac Studio M2 Ultra 128GB?

YES — Runs Great

C45Usable

○Estimated from fit model

Codestral 21B Pruned i1 needs ~30.0 GB VRAM. Mac Studio M2 Ultra 128GB has 92.2 GB. With Q4_K_M quantization, expect ~36 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: HighStack: 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, 36.2 tok/s, Runs well

30.0 GB required92.2 GB available

33% VRAM used

Fit status

Runs well

Decode

36.2 tok/s

TTFT

5345 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 Mac Studio M2 Ultra 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: 36.2 tok/s decode · 5.3s TTFT (warm) · 91 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	36.2 tok/s	2915 ms	420K
Coding	C	Runs well	36.2 tok/s	5345 ms	420K
Agentic Coding	C	Runs well	36.2 tok/s	7774 ms	420K
Reasoning	C	Runs well	36.2 tok/s	6317 ms	420K
RAG	C	Runs well	36.2 tok/s	9718 ms	420K

Quantization options

How Codestral 21B Pruned i1 (21B params) fits at each quantization level on Mac Studio M2 Ultra 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

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 PRO 6000 Blackwell Workstation Edition 96GBBudget pick

1792 GB/s (+992)

Raises estimated decode speed by about 225%.117.5 tok/s decode

Raises estimated decode speed by about 225%.

~$9,999 MSRP

👁 NVIDIA
RTX PRO 6000 Blackwell Server Edition 96GBBest value

1597 GB/s (+797)

Raises estimated decode speed by about 189%.104.7 tok/s decode

Raises estimated decode speed by about 189%.