Can GPT-OSS 20B run on AMD Instinct MI250X 128GB?

YES — Runs Great

S85Excellent

Estimated from fit model

GPT-OSS 20B needs ~29.0 GB VRAM. AMD Instinct MI250X 128GB has 128.0 GB. With Q4_K_M quantization, expect ~479 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) — 29.0 GB, 479.2 tok/s, Runs well

29.0 GB required128.0 GB available

23% VRAM used

Fit status

Runs well

Decode

479.2 tok/s

TTFT

404 ms

Safe context

128K

Memory

29.0 GB / 128.0 GB

Memory breakdown

Weights12.8 GB

KV Cache2.4 GB

Runtime0.9 GB

Headroom12.8 GB

See how fast it feels

See how fast it feelsGPT-OSS 20B 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: 479.2 tok/s decode · 404ms TTFT (warm) · 1198 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	479.2 tok/s	350 ms	128K
Coding	S	Runs well	479.2 tok/s	404 ms	128K
Agentic Coding	S	Runs well	479.2 tok/s	588 ms	128K
Reasoning	S	Runs well	479.2 tok/s	478 ms	128K
RAG	S	Runs well	479.2 tok/s	735 ms	128K

Inference speed

GPT-OSS 20B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for GPT-OSS 20B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~231 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.

GPU / Mac	Memory	Quant	Speed (tok/s)	Fits?
RTX 5090 32GB	32 GB	Q4_K_M	230.5	Fits
RTX 4090 24GB	24 GB	Q4_K_M	147.1	Fits
RX 7900 XTX 24GB	24 GB	Q4_K_M	132.7	Fits
RTX 3090 24GB	24 GB	Q4_K_M	125.8	Fits
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	106.9	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	89.1	Fits
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	84.5	Fits
RTX 4080 Super 16GB	16 GB	Q4_K_M	68.2	Heavy offload
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	66.0	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	66.0	Fits
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	46.1	Fits
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	42.2	Fits
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	40.4	Fits
RTX 4070 12GB	12 GB	Q4_K_M	24.2	Too big
RTX 3060 12GB	12 GB	Q4_K_M	15.2	Too big
RTX 4060 8GB	8 GB	Q4_K_M	5.7	Too big

Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.

Quantization options

How GPT-OSS 20B (21B params) fits at each quantization level on AMD Instinct MI250X 128GB (128.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	8.2 GB	Low	A77
Q3_K_S	3	10.3 GB	Low	A77
NVFP4	4	11.8 GB	Medium	A77
Q4_K_M	4	12.8 GB	Medium	A77
Q5_K_M	5	15.1 GB	High	A77
Q6_K	6	17.2 GB	High	A77
Q8_0	8	22.5 GB	Very High	A78
F16Best for your GPU	16	43.1 GB	Maximum	A81

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 MI250X 128GB can run

Model	Params	Grade	Decode
Devstral 2 123B Instruct	123B	S	36.2 tok/s
Qwen3-Coder 30B A3B Instruct	30.5B	S	377.4 tok/s
Qwen 3.5 27B	27B	S	163.7 tok/s
Qwen 3.6 27B	27B	S	102 tok/s
Qwen 3.5 122B A10B	122B	S	100.3 tok/s

Frequently asked questions

Can AMD Instinct MI250X 128GB run GPT-OSS 20B?

Yes, AMD Instinct MI250X 128GB can run GPT-OSS 20B with a S grade (Runs well). Expected decode speed: 479.2 tok/s.

How much VRAM does GPT-OSS 20B need?

GPT-OSS 20B (21B parameters) requires approximately 29.0 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 MI250X 128GB?

On AMD Instinct MI250X 128GB, GPT-OSS 20B achieves approximately 479.2 tokens per second decode speed with a time-to-first-token of 404ms using Q4_K_M quantization.

Can AMD Instinct MI250X 128GB run GPT-OSS 20B for coding?

For coding workloads, GPT-OSS 20B on AMD Instinct MI250X 128GB receives a S grade with 479.2 tok/s and 128K context.

What context window can GPT-OSS 20B use on AMD Instinct MI250X 128GB?

On AMD Instinct MI250X 128GB, 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 MI250X 128GB 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-mi250x-128gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: