Can Devstral Small 2 24B Instruct run on AMD Instinct MI250 128GB?

YES — Runs Great

S88Excellent

○Estimated from fit model

Devstral Small 2 24B Instruct needs ~30.8 GB VRAM. AMD Instinct MI250 128GB has 128.0 GB. With Q4_K_M quantization, expect ~160 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) — 30.8 GB, 159.8 tok/s, Runs well

30.8 GB required128.0 GB available

24% VRAM used

Fit status

Runs well

Decode

159.8 tok/s

TTFT

1212 ms

Safe context

256K

Memory

30.8 GB / 128.0 GB

Memory breakdown

Weights14.6 GB

KV Cache2.4 GB

Runtime0.9 GB

Headroom12.8 GB

See how fast it feels

See how fast it feelsDevstral Small 2 24B Instruct on AMD Instinct MI250 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: 159.8 tok/s decode · 1.2s TTFT (warm) · 400 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	159.8 tok/s	661 ms	256K
Coding	S	Runs well	159.8 tok/s	1212 ms	256K
Agentic Coding	S	Runs well	159.8 tok/s	1762 ms	256K
Reasoning	S	Runs well	159.8 tok/s	1432 ms	256K
RAG	S	Runs well	159.8 tok/s	2203 ms	256K

Quantization options

How Devstral Small 2 24B Instruct (24B params) fits at each quantization level on AMD Instinct MI250 128GB (128.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	9.4 GB	Low	A80
Q3_K_S	3	11.8 GB	Low	A80
NVFP4	4	13.4 GB	Medium	A80
Q4_K_M	4	14.6 GB	Medium	A80
Q5_K_M	5	17.3 GB	High	A80
Q6_K	6	19.7 GB	High	A80
Q8_0	8	25.7 GB	Very High	A81
F16Best for your GPU	16	49.2 GB	Maximum	A85

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 AMD Instinct MI250 128GB can run

Model	Params	Grade	Decode
👁 Mistral Devstral 2 123B Instruct	123B	S	31.5 tok/s
👁 Alibaba Qwen3-Coder 30B A3B Instruct	30.5B	S	329 tok/s
👁 Alibaba Qwen 3.5 27B	27B	S	142.7 tok/s
👁 Alibaba Qwen 3.6 27B	27B	S	88.9 tok/s
👁 Alibaba Qwen 3.5 122B A10B	122B	S	87.5 tok/s

Frequently asked questions

See all results for AMD Instinct MI250 128GB See all hardware for Devstral Small 2 24B Instruct

URL: https://willitrunai.com/can-run/devstral-small-2-24b-on-instinct-mi250-128gb

⇱ Devstral Small 2 24B Instruct on AMD Instinct MI250 128GB? …