Can Gemma 4 31B run on H100 NVL 188GB?

YES — Runs Great

A85Great

○Estimated from fit model

Gemma 4 31B needs ~53.4 GB VRAM. H100 NVL 188GB has 188.0 GB. With Q4_K_M quantization, expect ~354 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) — 53.4 GB, 354.2 tok/s, Runs well

53.4 GB required188.0 GB available

28% VRAM used

Fit status

Runs well

Decode

354.2 tok/s

TTFT

547 ms

Safe context

163K

Memory

53.4 GB / 188.0 GB

Memory breakdown

Weights18.7 GB

KV Cache14.6 GB

Runtime1.2 GB

Headroom18.8 GB

See how fast it feels

See how fast it feelsGemma 4 31B on H100 NVL 188GB
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: 354.2 tok/s decode · 547ms TTFT (warm) · 886 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	354.2 tok/s	350 ms	163K
Coding	A	Runs well	354.2 tok/s	547 ms	163K
Agentic Coding	S	Runs well	354.2 tok/s	795 ms	163K
Reasoning	A	Runs well	354.2 tok/s	646 ms	163K
RAG	S	Runs well	354.2 tok/s	994 ms	163K

Quantization options

How Gemma 4 31B (30.700000762939453B params) fits at each quantization level on H100 NVL 188GB (188.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	12.0 GB	Low	A74
Q3_K_S	3	15.0 GB	Low	A74
NVFP4	4	17.2 GB	Medium	A74
Q4_K_M	4	18.7 GB	Medium	A74
Q5_K_M	5	22.1 GB	High	A75
Q6_K	6	25.2 GB	High	A75
Q8_0	8	32.8 GB	Very High	A76
F16Best for your GPU	16	62.9 GB	Maximum	A79

Get started

Copy-paste commands to run Gemma 4 31B on your machine.

Run

ollama run gemma4:31b

Your hardware

More models your H100 NVL 188GB can run

Model	Params	Grade	Decode
👁 Mistral Devstral 2 123B Instruct	123B	S	91.6 tok/s
👁 Alibaba Qwen 3.5 122B A10B	122B	S	254 tok/s
👁 DeepSeek DeepSeek V4 Flash	284B	S	136.1 tok/s
👁 Alibaba Qwen 3.6 35B A3B	35B	S	802.9 tok/s
👁 Alibaba Qwen 3.5 35B A3B	35B	S	873.2 tok/s

Frequently asked questions

See all results for H100 NVL 188GB See all hardware for Gemma 4 31B

URL: https://willitrunai.com/can-run/gemma-4-31b-on-h100-nvl-188gb