Can GPT-OSS 20B run on RTX 4000 Ada 20GB?

YES — Tight Fit

S91Excellent

Estimated from fit model

GPT-OSS 20B needs ~18.5 GB VRAM. RTX 4000 Ada 20GB has 20.0 GB. With Q4_K_M quantization, expect ~54 tok/s.

Runtime: OllamaCapacity: TightBandwidth: LowStack: BasicBottleneck: 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) — 18.5 GB, 53.9 tok/s, Tight fit

18.5 GB required20.0 GB available

93% VRAM used

Fit status

Tight fit

Decode

53.9 tok/s

TTFT

3591 ms

Safe context

26K

Memory

18.5 GB / 20.0 GB

Memory breakdown

Weights12.8 GB

KV Cache2.4 GB

Runtime1.2 GB

Headroom2.0 GB

See how fast it feels

See how fast it feelsGPT-OSS 20B on RTX 4000 Ada 20GB
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: 53.9 tok/s decode · 3.6s TTFT (warm) · 135 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

Very little memory headroom

You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.

Best improvement path

Buy headroom, not only minimum fit

A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	S	Tight fit	53.9 tok/s	1959 ms	26K
Coding	S	Tight fit	53.9 tok/s	3591 ms	26K
Agentic Coding	S	Runs with offload (needs ~0.5 GB host RAM)	36.9 tok/s	7636 ms	26K
Reasoning	S	Tight fit	53.9 tok/s	4244 ms	26K
RAG	S	Runs with offload (needs ~0.5 GB host RAM)	36.9 tok/s	9545 ms	26K

Quantization options

How GPT-OSS 20B (21B params) fits at each quantization level on RTX 4000 Ada 20GB (20.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	8.2 GB	Low	S88
Q3_K_S	3	10.3 GB	Low	S89
NVFP4	4	11.8 GB	Medium	S89
Q4_K_M	4	12.8 GB	Medium	S89
Q5_K_MBest for your GPU	5	15.1 GB	High	S88
Q6_K	6	17.2 GB	High	F0
Q8_0	8	22.5 GB	Very High	F0
F16	16	43.1 GB	Maximum	F0

Get started

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

Run

ollama run gpt-oss

Your hardware

More models your RTX 4000 Ada 20GB can run

Model	Params	Grade	Decode
Qwen3-Coder 30B A3B Instruct	30.5B	A	23.2 tok/s
Qwen 3.5 27B	27B	A	10.4 tok/s
Qwen 3.6 27B	27B	S	13 tok/s
Qwen3-VL 30B A3B Instruct	30B	A	24.6 tok/s
Magistral Small 2507	24B	S	15 tok/s

Frequently asked questions

Can RTX 4000 Ada 20GB run GPT-OSS 20B?

Yes, RTX 4000 Ada 20GB can run GPT-OSS 20B with a S grade (Tight fit). Expected decode speed: 53.9 tok/s.

How much VRAM does GPT-OSS 20B need?

GPT-OSS 20B (21B parameters) requires approximately 18.5 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 RTX 4000 Ada 20GB?

On RTX 4000 Ada 20GB, GPT-OSS 20B achieves approximately 53.9 tokens per second decode speed with a time-to-first-token of 3591ms using Q4_K_M quantization.

Can RTX 4000 Ada 20GB run GPT-OSS 20B for coding?

For coding workloads, GPT-OSS 20B on RTX 4000 Ada 20GB receives a S grade with 53.9 tok/s and 26K context.

What context window can GPT-OSS 20B use on RTX 4000 Ada 20GB?

On RTX 4000 Ada 20GB, GPT-OSS 20B can safely use up to 26K tokens of context. The model's official context limit is 128K, but available memory constrains the safe maximum.

What should I upgrade first if GPT-OSS 20B feels slow on RTX 4000 Ada 20GB?

Buy headroom, not only minimum fit. A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.

See all results for RTX 4000 Ada 20GB 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-rtx-4000-ada-20gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: