Can GPT-OSS 20B run on AMD Instinct MI350X 288GB?

YES — Runs Great

A84Great

Estimated from fit model

GPT-OSS 20B needs ~45.0 GB VRAM. AMD Instinct MI350X 288GB has 288.0 GB. With Q4_K_M quantization, expect ~1121 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) — 45.0 GB, 1121.1 tok/s, Runs well

45.0 GB required288.0 GB available

16% VRAM used

Fit status

Runs well

Decode

1121.1 tok/s

TTFT

350 ms

Safe context

128K

Memory

45.0 GB / 288.0 GB

Memory breakdown

Weights12.8 GB

KV Cache2.4 GB

Runtime0.9 GB

Headroom28.8 GB

See how fast it feels

See how fast it feelsGPT-OSS 20B 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: 1121.1 tok/s decode · 350ms TTFT (warm) · 2803 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	1121.1 tok/s	350 ms	128K
Coding	A	Runs well	1121.1 tok/s	350 ms	128K
Agentic Coding	A	Runs well	1121.1 tok/s	350 ms	128K
Reasoning	A	Runs well	1121.1 tok/s	350 ms	128K
RAG	A	Runs well	1121.1 tok/s	350 ms	128K

Quantization options

How GPT-OSS 20B (21B params) fits at each quantization level on AMD Instinct MI350X 288GB (288.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	8.2 GB	Low	A74
Q3_K_S	3	10.3 GB	Low	A74
NVFP4	4	11.8 GB	Medium	A75
Q4_K_M	4	12.8 GB	Medium	A75
Q5_K_M	5	15.1 GB	High	A75
Q6_K	6	17.2 GB	High	A75
Q8_0	8	22.5 GB	Very High	A75
F16Best for your GPU	16	43.1 GB	Maximum	A77

Get started

Copy-paste commands to run GPT-OSS 20B on your machine.

Run

ollama run gpt-oss

Your hardware

More models your AMD Instinct MI350X 288GB can run

Model	Params	Grade	Decode
Qwen 3.5 397B A17B	397B	S	78.9 tok/s
Devstral 2 123B Instruct	123B	S	84.6 tok/s
Qwen3-Coder 30B A3B Instruct	30.5B	S	883.1 tok/s
Qwen 3.5 27B	27B	S	378 tok/s
Qwen 3.6 27B	27B	S	238.7 tok/s

Frequently asked questions

Can AMD Instinct MI350X 288GB run GPT-OSS 20B?

Yes, AMD Instinct MI350X 288GB can run GPT-OSS 20B with a A grade (Runs well). Expected decode speed: 1121.1 tok/s.

How much VRAM does GPT-OSS 20B need?

GPT-OSS 20B (21B parameters) requires approximately 45.0 GB of memory with Q4_K_M quantization.

What is the best quantization for GPT-OSS 20B?

The recommended quantization for GPT-OSS 20B is Q4_K_M, which balances quality and memory efficiency.

What speed will GPT-OSS 20B run at on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, GPT-OSS 20B achieves approximately 1121.1 tokens per second decode speed with a time-to-first-token of 350ms using Q4_K_M quantization.

Can AMD Instinct MI350X 288GB run GPT-OSS 20B for coding?

For coding workloads, GPT-OSS 20B on AMD Instinct MI350X 288GB receives a A grade with 1121.1 tok/s and 128K context.

What context window can GPT-OSS 20B use on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, GPT-OSS 20B can safely use up to 128K tokens of context. The model's official context limit is 128K, but available memory constrains the safe maximum.

See all results for AMD Instinct MI350X 288GB See all hardware for GPT-OSS 20B

Embed this result▼

Paste this snippet into any page to show a live fit card.

<iframe src="https://willitrunai.com/embed/gpt-oss-20b-on-instinct-mi350x-288gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview:

Workload

Grade

Fit

Decode

TTFT

Context

Chat

Runs well

1121.1 tok/s

350 ms

128K

Coding

Runs well

1121.1 tok/s

350 ms

128K

Agentic Coding

Runs well

1121.1 tok/s

350 ms

128K

Reasoning

Runs well

1121.1 tok/s

350 ms

128K

RAG

Runs well

1121.1 tok/s

350 ms

128K

Quantization options

How GPT-OSS 20B (21B params) fits at each quantization level on AMD Instinct MI350X 288GB (288.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	8.2 GB	Low	A74
Q3_K_S	3	10.3 GB	Low	A74
NVFP4	4	11.8 GB	Medium	A75
Q4_K_M	4	12.8 GB	Medium	A75
Q5_K_M	5	15.1 GB	High	A75
Q6_K	6	17.2 GB	High	A75
Q8_0	8	22.5 GB	Very High	A75
F16Best for your GPU	16	43.1 GB	Maximum	A77

Model

Params

Grade

Decode

Capabilities

Qwen 3.5 397B A17B

397B

78.9 tok/s

Devstral 2 123B Instruct

123B

84.6 tok/s

Qwen3-Coder 30B A3B Instruct

30.5B

883.1 tok/s

Qwen 3.5 27B

27B

378 tok/s

Qwen 3.6 27B

27B

238.7 tok/s

Frequently asked questions

Can AMD Instinct MI350X 288GB run GPT-OSS 20B?

Yes, AMD Instinct MI350X 288GB can run GPT-OSS 20B with a A grade (Runs well). Expected decode speed: 1121.1 tok/s.

How much VRAM does GPT-OSS 20B need?

GPT-OSS 20B (21B parameters) requires approximately 45.0 GB of memory with Q4_K_M quantization.

What is the best quantization for GPT-OSS 20B?

The recommended quantization for GPT-OSS 20B is Q4_K_M, which balances quality and memory efficiency.

What speed will GPT-OSS 20B run at on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, GPT-OSS 20B achieves approximately 1121.1 tokens per second decode speed with a time-to-first-token of 350ms using Q4_K_M quantization.

Can AMD Instinct MI350X 288GB run GPT-OSS 20B for coding?

For coding workloads, GPT-OSS 20B on AMD Instinct MI350X 288GB receives a A grade with 1121.1 tok/s and 128K context.

What context window can GPT-OSS 20B use on AMD Instinct MI350X 288GB?

On AMD Instinct MI350X 288GB, GPT-OSS 20B can safely use up to 128K tokens of context. The model's official context limit is 128K, but available memory constrains the safe maximum.