Can GPT-OSS 120B run on NVIDIA GH200 96GB?

YES — Tight Fit

S92Excellent

○Estimated from fit model

GPT-OSS 120B needs ~86.8 GB VRAM. NVIDIA GH200 96GB has 96.0 GB. With Q4_K_M quantization, expect ~49 tok/s.

Runtime: llama.cppCapacity: TightBandwidth: 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) — 86.8 GB, 49.4 tok/s, Tight fit

86.8 GB required96.0 GB available

90% VRAM used

Fit status

Tight fit

Decode

49.4 tok/s

TTFT

3921 ms

Safe context

46K

Memory

86.8 GB / 96.0 GB

Memory breakdown

Weights71.4 GB

KV Cache4.9 GB

Runtime0.9 GB

Headroom9.6 GB

See how fast it feels

See how fast it feelsGPT-OSS 120B on NVIDIA GH200 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: 49.4 tok/s decode · 3.9s TTFT (warm) · 123 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	Tight fit	49.4 tok/s	2139 ms	46K
Coding	S	Tight fit	49.4 tok/s	3921 ms	46K
Agentic Coding	S	Runs with offload	49.4 tok/s	5704 ms	46K
Reasoning	S	Tight fit	49.4 tok/s	4634 ms	46K
RAG	S	Runs with offload	49.4 tok/s	7130 ms	46K

Quantization options

How GPT-OSS 120B (117B params) fits at each quantization level on NVIDIA GH200 96GB (96.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	45.6 GB	Low	S87
Q3_K_S	3	57.3 GB	Low	S88
NVFP4	4	65.5 GB	Medium	S88
Q4_K_MBest for your GPU	4	71.4 GB	Medium	S88
Q5_K_M	5	84.2 GB	High	F0
Q6_K	6	95.9 GB	High	F0
Q8_0	8	125.2 GB	Very High	F0
F16	16	239.8 GB	Maximum	F0

Get started

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

Run

ollama run gpt-oss:120b

Your hardware

More models your NVIDIA GH200 96GB can run

Model	Params	Grade	Decode
👁 Mistral Devstral 2 123B Instruct	123B	S	47 tok/s
👁 Alibaba Qwen 3.5 122B A10B	122B	S	130.3 tok/s
👁 Mistral Mistral Small 4 119B	119B	S	141.2 tok/s

Frequently asked questions

See all results for NVIDIA GH200 96GB See all hardware for GPT-OSS 120B

URL: https://willitrunai.com/can-run/gpt-oss-120b-on-gh200-96gb

⇱ GPT-OSS 120B on NVIDIA GH200 96GB? TIGHT FIT