Can Gemma 4 31B run on Mac Studio M3 Ultra 96GB?

YES — Runs Great

S88Excellent

○Estimated from fit model

Gemma 4 31B needs ~44.6 GB VRAM. Mac Studio M3 Ultra 96GB has 69.1 GB. With Q4_K_M quantization, expect ~23 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: 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) — 44.6 GB, 23.7 tok/s, Runs well

44.6 GB required69.1 GB available

65% VRAM used

Fit status

Runs well

Decode

23.7 tok/s

TTFT

8181 ms

Safe context

43K

Memory

44.6 GB / 69.1 GB

Memory breakdown

Weights18.7 GB

KV Cache14.6 GB

Runtime0.9 GB

Headroom10.4 GB

See how fast it feels

See how fast it feelsGemma 4 31B on Mac Studio M3 Ultra 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: 23.7 tok/s decode · 8.2s TTFT (warm) · 59 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

Shared-memory contention still exists

The OS, browser, and inference runtime all compete for the same physical memory pool, so real-world headroom is less forgiving than raw capacity suggests.

Best improvement path

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	S	Runs well	22.5 tok/s	4685 ms	43K
Coding	S	Runs well	22.5 tok/s	8590 ms	43K
Agentic Coding	S	Tight fit	22.5 tok/s	12495 ms	43K
Reasoning	S	Runs well	22.5 tok/s	10152 ms	43K
RAG	S	Tight fit	22.5 tok/s	15618 ms	43K

Quantization options

How Gemma 4 31B (30.700000762939453B params) fits at each quantization level on Mac Studio M3 Ultra 96GB (69.1 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	12.0 GB	Low	A78
Q3_K_S	3	15.0 GB	Low	A79
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 Mac Studio M3 Ultra 96GB can run

Model	Params	Grade	Decode	Capabilities
👁 Alibaba Qwen 3.6 35B A3B	35B	S	70.8 tok/s
👁 Alibaba

Frequently asked questions

See all results for Mac Studio M3 Ultra 96GB See all hardware for Gemma 4 31B

URL: https://willitrunai.com/can-run/gemma-4-31b-on-m3-ultra-96gb

⇱