Can GPT-OSS 120B run on AMD Instinct MI350X 288GB?

YES — Runs Great

S90Excellent

○Estimated from fit model

GPT-OSS 120B needs ~106.0 GB VRAM. AMD Instinct MI350X 288GB has 288.0 GB. With Q4_K_M quantization, expect ~82 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) — 106.0 GB, 89.0 tok/s, Runs well

106.0 GB required288.0 GB available

37% VRAM used

Fit status

Runs well

Decode

89.0 tok/s

TTFT

2176 ms

Safe context

131K

Memory

106.0 GB / 288.0 GB

Memory breakdown

Weights71.4 GB

KV Cache4.9 GB

Runtime0.9 GB

Headroom28.8 GB

See how fast it feels

See how fast it feelsGPT-OSS 120B on AMD Instinct MI350X 288GB
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: 89.0 tok/s decode · 2.2s TTFT (warm) · 223 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	89.0 tok/s	1187 ms	131K
Coding	S	Runs well	81.8 tok/s	2366 ms	131K
Agentic Coding	S	Runs well	89.0 tok/s	3165 ms	131K
Reasoning	S	Runs well	89.0 tok/s	2571 ms	131K
RAG	S	Runs well	89.0 tok/s	3956 ms	131K

Quantization options

How GPT-OSS 120B (117B params) fits at each quantization level on AMD Instinct MI350X 288GB (288.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	45.6 GB	Low	A79
Q3_K_S	3	57.3 GB	Low	A80
NVFP4	4

Get started

Copy-paste commands to run GPT-OSS 120B on your machine.

Run

ollama run gpt-oss:120b

Your hardware

More models your AMD Instinct MI350X 288GB can run

Model	Params	Grade	Decode	Capabilities
👁 Alibaba Qwen 3.5 397B A17B	397B	S	78.9 tok/s
👁 Mistral Devstral 2 123B Instruct	123B	S

Frequently asked questions

See all results for AMD Instinct MI350X 288GB See all hardware for GPT-OSS 120B

URL: https://willitrunai.com/can-run/gpt-oss-120b-on-instinct-mi350x-288gb

⇱