Can Devstral 2 123B Instruct run on Mac Studio M3 Ultra 256GB?

YES — Runs Great

S90Excellent

○Estimated from fit model

Devstral 2 123B Instruct needs ~108.9 GB VRAM. Mac Studio M3 Ultra 256GB has 184.3 GB. With Q4_K_M quantization, expect ~7 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: HighStack: 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) — 108.9 GB, 8.1 tok/s, Runs well

108.9 GB required184.3 GB available

59% VRAM used

Fit status

Runs well

Decode

8.1 tok/s

TTFT

23984 ms

Safe context

241K

Memory

108.9 GB / 184.3 GB

Memory breakdown

Weights75.0 GB

KV Cache5.4 GB

Runtime0.9 GB

Headroom27.6 GB

See how fast it feels

See how fast it feelsDevstral 2 123B Instruct on Mac Studio M3 Ultra 256GB
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: 8.1 tok/s decode · 24.0s TTFT (warm) · 20 tok/s prefill

What limits this setup

The model fits in shared memory, but shared-memory bandwidth is now the real limiter.

Fit does not mean dedicated-VRAM speed

Unified or shared memory can make a model technically fit, but sustained tokens per second may still trail a discrete high-bandwidth GPU with less total memory.

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

Prioritize bandwidth, not only capacity

If this workload feels slow, the next useful step is often a GPU tier with materially faster memory bandwidth rather than only a small bump in capacity.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	S	Runs well	7.4 tok/s	14227 ms	241K
Coding	S	Runs well	7.4 tok/s	26082 ms	241K
Agentic Coding	S	Runs well	7.4 tok/s	37938 ms	241K
Reasoning	S	Runs well	7.4 tok/s	30825 ms	241K
RAG	S	Runs well	7.4 tok/s	47423 ms	241K

Quantization options

How Devstral 2 123B Instruct (123B params) fits at each quantization level on Mac Studio M3 Ultra 256GB (184.3 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	48.0 GB	Low	A85
Q3_K_S	3	60.3 GB	Low	S86
NVFP4	4

Get started

Copy-paste commands to run Devstral 2 123B Instruct on your machine.

Run

lms load Devstral-2-123B-Instruct-2512 && lms server start

Frequently asked questions

See all results for Mac Studio M3 Ultra 256GB See all hardware for Devstral 2 123B Instruct

URL: https://willitrunai.com/can-run/devstral-2-123b-on-m3-ultra-256gb

⇱