Can Devstral Small 2 24B Instruct run on RTX PRO 4500 Blackwell 32GB?

YES — Runs Great

S96Excellent

○Estimated from fit model

Devstral Small 2 24B Instruct needs ~21.5 GB VRAM. RTX PRO 4500 Blackwell 32GB has 32.0 GB. With Q4_K_M quantization, expect ~55 tok/s.

Runtime: OllamaCapacity: RoomyBandwidth: HighStack: BasicBottleneck: 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) — 21.5 GB, 55.3 tok/s, Runs well

21.5 GB required32.0 GB available

67% VRAM used

Fit status

Runs well

Decode

55.3 tok/s

TTFT

3503 ms

Safe context

85K

Memory

21.5 GB / 32.0 GB

Memory breakdown

Weights14.6 GB

KV Cache2.4 GB

Runtime1.2 GB

Headroom3.2 GB

See how fast it feels

See how fast it feelsDevstral Small 2 24B Instruct on RTX PRO 4500 Blackwell 32GB
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: 55.3 tok/s decode · 3.5s TTFT (warm) · 138 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

No major red flags

This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.

Best improvement path

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	S	Runs well	55.3 tok/s	1911 ms	85K
Coding	S	Runs well	55.3 tok/s	3503 ms	85K
Agentic Coding	S	Runs well	55.3 tok/s	5095 ms	85K
Reasoning	S	Runs well	55.3 tok/s	4140 ms	85K
RAG	S	Runs well	55.3 tok/s	6369 ms	85K

Quantization options

How Devstral Small 2 24B Instruct (24B params) fits at each quantization level on RTX PRO 4500 Blackwell 32GB (32.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	9.4 GB	Low	S87
Q3_K_S	3	11.8 GB	Low	S88
NVFP4	4

Get started

Copy-paste commands to run Devstral Small 2 24B Instruct on your machine.

Run

ollama run devstral-small-2

Your hardware

More models your RTX PRO 4500 Blackwell 32GB can run

Model	Params	Grade	Decode	Capabilities
👁 Alibaba Qwen3-Coder 30B A3B Instruct	30.5B	S	113.8 tok/s
👁 Alibaba Qwen 3.5 27B	27B	S	49.4 tok/s

Frequently asked questions

See all results for RTX PRO 4500 Blackwell 32GB See all hardware for Devstral Small 2 24B Instruct

URL: https://willitrunai.com/can-run/devstral-small-2-24b-on-rtx-pro-4500-blackwell-32gb

⇱