Can EXAONE 4.0 32B run on AMD Instinct MI250X 128GB?

YES — Runs Great

A83Great

○Estimated from fit model

EXAONE 4.0 32B needs ~37.1 GB VRAM. AMD Instinct MI250X 128GB has 128.0 GB. With Q4_K_M quantization, expect ~138 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) — 37.1 GB, 138.1 tok/s, Runs well

37.1 GB required128.0 GB available

29% VRAM used

Fit status

Runs well

Decode

138.1 tok/s

TTFT

1402 ms

Safe context

131K

Memory

37.1 GB / 128.0 GB

Memory breakdown

Weights19.5 GB

KV Cache3.9 GB

Runtime0.9 GB

Headroom12.8 GB

See how fast it feels

See how fast it feelsEXAONE 4.0 32B on AMD Instinct MI250X 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: 138.1 tok/s decode · 1.4s TTFT (warm) · 345 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	A	Runs well	138.1 tok/s	765 ms	131K
Coding	A	Runs well	138.1 tok/s	1402 ms	131K
Agentic Coding	A	Runs well	138.1 tok/s	2039 ms	131K
Reasoning	A	Runs well	138.1 tok/s	1657 ms	131K
RAG	A	Runs well	138.1 tok/s	2549 ms	131K

Quantization options

How EXAONE 4.0 32B (32B params) fits at each quantization level on AMD Instinct MI250X 128GB (128.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	12.5 GB	Low	A74
Q3_K_S	3	15.7 GB	Low	A74
NVFP4	4	17.9 GB	Medium	A74
Q4_K_M	4	19.5 GB	Medium	A74
Q5_K_M	5	23.0 GB	High	A74
Q6_K	6	26.2 GB	High	A75
Q8_0	8	34.2 GB	Very High	A76
F16Best for your GPU	16	65.6 GB	Maximum	A81

Get started

Copy-paste commands to run EXAONE 4.0 32B on your machine.

Run

ollama run exaone-4:32b

Your hardware

More models your AMD Instinct MI250X 128GB can run

Model	Params	Grade	Decode
👁 Mistral Devstral 2 123B Instruct	123B	S	36.2 tok/s
👁 Alibaba Qwen 3.5 122B A10B	122B	S	100.3 tok/s
👁 Alibaba Qwen 3.6 35B A3B	35B	S	317.2 tok/s
👁 Alibaba Qwen 3.5 35B A3B	35B	S	344.9 tok/s
👁 Mistral Mistral Small 4 119B	119B	S	108.8 tok/s

Frequently asked questions

See all results for AMD Instinct MI250X 128GB See all hardware for EXAONE 4.0 32B

URL: https://willitrunai.com/can-run/exaone-4-32b-on-instinct-mi250x-128gb

⇱ EXAONE 4.0 32B on AMD Instinct MI250X 128GB? YES