Can Gemma 4 31B run on NVIDIA A800 80GB?

YES — Runs Great

S90Excellent

○Estimated from fit model

Gemma 4 31B needs ~42.6 GB VRAM. NVIDIA A800 80GB has 80.0 GB. With Q4_K_M quantization, expect ~81 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) — 42.6 GB, 84.6 tok/s, Runs well

42.6 GB required80.0 GB available

53% VRAM used

Fit status

Runs well

Decode

84.6 tok/s

TTFT

2288 ms

Safe context

57K

Memory

42.6 GB / 80.0 GB

Memory breakdown

Weights18.7 GB

KV Cache14.6 GB

Runtime1.2 GB

Headroom8.0 GB

See how fast it feels

See how fast it feelsGemma 4 31B on NVIDIA A800 80GB
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: 84.6 tok/s decode · 2.3s TTFT (warm) · 212 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	80.6 tok/s	1310 ms	57K
Coding	S	Runs well	80.6 tok/s	2402 ms	57K
Agentic Coding	S	Runs well	80.6 tok/s	3494 ms	57K
Reasoning	S	Runs well	80.6 tok/s	2839 ms	57K
RAG	S	Runs well	80.6 tok/s	4368 ms	57K

Quantization options

How Gemma 4 31B (30.700000762939453B params) fits at each quantization level on NVIDIA A800 80GB (80.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	12.0 GB	Low	A77
Q3_K_S	3	15.0 GB	Low	A78
NVFP4	4

Get started

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

Run

ollama run gemma4:31b

Your hardware

More models your NVIDIA A800 80GB can run

Model	Params	Grade	Decode	Capabilities
👁 Mistral Devstral 2 123B Instruct	123B	A	15.5 tok/s
👁 Alibaba Qwen 3.5 122B A10B	122B	A

Frequently asked questions

See all results for NVIDIA A800 80GB See all hardware for Gemma 4 31B

URL: https://willitrunai.com/can-run/gemma-4-31b-on-a800-80gb

⇱