Can Qwen 3.5 122B A10B run on AMD Instinct MI325X 256GB?

YES — Runs Great

S93Excellent

○Estimated from fit model

Qwen 3.5 122B A10B needs ~103.4 GB VRAM. AMD Instinct MI325X 256GB has 256.0 GB. With Q4_K_M quantization, expect ~176 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) — 103.4 GB, 176.1 tok/s, Runs well

103.4 GB required256.0 GB available

40% VRAM used

Fit status

Runs well

Decode

176.1 tok/s

TTFT

1099 ms

Safe context

131K

Memory

103.4 GB / 256.0 GB

Memory breakdown

Weights74.4 GB

KV Cache2.4 GB

Runtime0.9 GB

Headroom25.6 GB

See how fast it feels

See how fast it feelsQwen 3.5 122B A10B on AMD Instinct MI325X 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: 176.1 tok/s decode · 1.1s TTFT (warm) · 440 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	176.1 tok/s	600 ms	131K
Coding	S	Runs well	176.1 tok/s	1099 ms	131K
Agentic Coding	S	Runs well	176.1 tok/s	1599 ms	131K
Reasoning	S	Runs well	176.1 tok/s	1299 ms	131K
RAG	S	Runs well	176.1 tok/s	1999 ms	131K

Quantization options

How Qwen 3.5 122B A10B (122B params) fits at each quantization level on AMD Instinct MI325X 256GB (256.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	47.6 GB	Low	A82
Q3_K_S	3	59.8 GB	Low	A83
NVFP4	4	68.3 GB	Medium	A84
Q4_K_M	4	74.4 GB	Medium	A84
Q5_K_M	5	87.8 GB	High	S85
Q6_K	6	100.0 GB	High	S86
Q8_0Best for your GPU	8	130.5 GB	Very High	S89
F16	16	250.1 GB	Maximum	F0

Get started

Copy-paste commands to run Qwen 3.5 122B A10B on your machine.

Run

lms load Qwen3.5-122B-A10B-Instruct && lms server start

Your hardware

More models your AMD Instinct MI325X 256GB can run

Model	Params	Grade	Decode	Capabilities
👁 Alibaba Qwen 3.5 397B A17B	397B	A	39.2 tok/s
👁 Mistral Devstral 2 123B Instruct	123B	S	63.5 tok/s

Frequently asked questions

See all results for AMD Instinct MI325X 256GB See all hardware for Qwen 3.5 122B A10B

URL: https://willitrunai.com/can-run/qwen-3.5-122b-a10b-on-instinct-mi325x-256gb

⇱ Qwen 3.5 122B A10B on AMD Instinct MI325X 256GB? YES