Can GPT-OSS 20B run on RTX PRO 6000 Blackwell Server Edition 96GB?

YES — Runs Great

S86Excellent

○Estimated from fit model

GPT-OSS 20B needs ~26.1 GB VRAM. RTX PRO 6000 Blackwell Server Edition 96GB has 96.0 GB. With Q4_K_M quantization, expect ~258 tok/s.

Runtime: OllamaCapacity: RoomyBandwidth: HighStack: 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) — 26.1 GB, 257.5 tok/s, Runs well

26.1 GB required96.0 GB available

27% VRAM used

Fit status

Runs well

Decode

257.5 tok/s

TTFT

752 ms

Safe context

128K

Memory

26.1 GB / 96.0 GB

Memory breakdown

Weights12.8 GB

KV Cache2.4 GB

Runtime1.2 GB

Headroom9.6 GB

See how fast it feels

See how fast it feelsGPT-OSS 20B on RTX PRO 6000 Blackwell Server Edition 96GB
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: 257.5 tok/s decode · 752ms TTFT (warm) · 644 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	257.5 tok/s	410 ms	128K
Coding	S	Runs well	257.5 tok/s	752 ms	128K
Agentic Coding	S	Runs well	257.5 tok/s	1093 ms	128K
Reasoning	S	Runs well	257.5 tok/s	888 ms	128K
RAG	S	Runs well	257.5 tok/s	1367 ms	128K

Quantization options

How GPT-OSS 20B (21B params) fits at each quantization level on RTX PRO 6000 Blackwell Server Edition 96GB (96.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	8.2 GB	Low	A78
Q3_K_S	3	10.3 GB	Low	A78
NVFP4	4	11.8 GB	Medium	A78
Q4_K_M	4	12.8 GB	Medium	A78
Q5_K_M	5	15.1 GB	High	A78
Q6_K	6	17.2 GB	High	A79
Q8_0	8	22.5 GB	Very High	A79
F16Best for your GPU	16	43.1 GB	Maximum	A84

Get started

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

Run

ollama run gpt-oss

Your hardware

More models your RTX PRO 6000 Blackwell Server Edition 96GB can run

Model	Params	Grade	Decode
👁 Mistral Devstral 2 123B Instruct	123B	S	19.4 tok/s
👁 Alibaba Qwen3-Coder 30B A3B Instruct	30.5B	S	202.8 tok/s
👁 Alibaba Qwen 3.5 27B	27B	S	88 tok/s
👁 Alibaba Qwen 3.6 27B	27B	S	88.2 tok/s
👁 Alibaba Qwen 3.5 122B A10B	122B	S	53.9 tok/s

Frequently asked questions

See all results for RTX PRO 6000 Blackwell Server Edition 96GB See all hardware for GPT-OSS 20B

URL: https://willitrunai.com/can-run/gpt-oss-20b-on-rtx-pro-6000-blackwell-server-96gb

⇱ GPT-OSS 20B on RTX PRO 6000 Blackwell Server Edition 96GB? …