Can Gemma 4 31B run on Gaudi 3 128GB?

YES — Runs Great

S87Excellent

Estimated from fit model

Gemma 4 31B needs ~47.1 GB VRAM. Gaudi 3 128GB has 128.0 GB. With Q4_K_M quantization, expect ~90 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) — 47.1 GB, 90.2 tok/s, Runs well

47.1 GB required128.0 GB available

37% VRAM used

Fit status

Runs well

Decode

90.2 tok/s

TTFT

2145 ms

Safe context

104K

Memory

47.1 GB / 128.0 GB

Memory breakdown

Weights18.7 GB

KV Cache14.6 GB

Runtime0.9 GB

Headroom12.8 GB

See how fast it feels

See how fast it feelsGemma 4 31B on Gaudi 3 128GB
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: 90.2 tok/s decode · 2.1s TTFT (warm) · 226 tok/s prefill

What limits this setup

The raw memory story may look fine, but the software ecosystem is still a constraint here.

Runtime ecosystem is narrower than CUDA

Intel GPUs can look attractive on memory per dollar, but local AI tooling, kernels, and model coverage are still broader and easier on CUDA today.

Best improvement path

Prefer CUDA if you want the path of least resistance

If your goal is maximum runtime coverage, easier troubleshooting, and better support for new local AI releases, CUDA is usually still the safer upgrade path.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	S	Runs well	90.2 tok/s	1170 ms	104K
Coding	S	Runs well	90.2 tok/s	2145 ms	104K
Agentic Coding	S	Runs well	90.2 tok/s	3120 ms	104K
Reasoning	S	Runs well	90.2 tok/s	2535 ms	104K
RAG	S	Runs well	90.2 tok/s	3900 ms	104K

Quantization options

How Gemma 4 31B (30.700000762939453B params) fits at each quantization level on Gaudi 3 128GB (128.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	12.0 GB	Low	A75
Q3_K_S	3	15.0 GB	Low	A76
NVFP4	4	17.2 GB	Medium	A76
Q4_K_M	4	18.7 GB	Medium	A76
Q5_K_M	5	22.1 GB	High	A76
Q6_K	6	25.2 GB	High	A76
Q8_0	8	32.8 GB	Very High	A78
F16Best for your GPU	16	62.9 GB	Maximum	A83

Get started

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

Run

ollama run gemma4:31b

Your hardware

More models your Gaudi 3 128GB can run

Model	Params	Grade	Decode
Devstral 2 123B Instruct	123B	S	37.5 tok/s
Qwen 3.5 122B A10B	122B	S	104.1 tok/s
Qwen 3.6 35B A3B	35B	S	329.1 tok/s
Qwen 3.5 35B A3B	35B	S	357.9 tok/s
Qwen 3 32B	32B	S	144.3 tok/s

Frequently asked questions

Can Gaudi 3 128GB run Gemma 4 31B?

Yes, Gaudi 3 128GB can run Gemma 4 31B with a S grade (Runs well). Expected decode speed: 90.2 tok/s.

How much VRAM does Gemma 4 31B need?

Gemma 4 31B (30.700000762939453B parameters) requires approximately 47.1 GB of memory with Q4_K_M quantization.

What is the best quantization for Gemma 4 31B?

The recommended quantization for Gemma 4 31B is Q4_K_M, which balances quality and memory efficiency.

What speed will Gemma 4 31B run at on Gaudi 3 128GB?

On Gaudi 3 128GB, Gemma 4 31B achieves approximately 90.2 tokens per second decode speed with a time-to-first-token of 2145ms using Q4_K_M quantization.

Can Gaudi 3 128GB run Gemma 4 31B for coding?

For coding workloads, Gemma 4 31B on Gaudi 3 128GB receives a S grade with 90.2 tok/s and 104K context.

What context window can Gemma 4 31B use on Gaudi 3 128GB?

On Gaudi 3 128GB, Gemma 4 31B can safely use up to 104K tokens of context. The model's official context limit is 256K, but available memory constrains the safe maximum.

What should I upgrade first if Gemma 4 31B feels slow on Gaudi 3 128GB?

Prefer CUDA if you want the path of least resistance. If your goal is maximum runtime coverage, easier troubleshooting, and better support for new local AI releases, CUDA is usually still the safer upgrade path.

Would CUDA be a better path than Gaudi 3 128GB for Gemma 4 31B?

Often yes, if your goal is the easiest setup and the widest runtime support. Intel can offer attractive memory capacity, but CUDA still tends to win on tooling maturity, guides, kernels, and model coverage for local AI.

See all results for Gaudi 3 128GB See all hardware for Gemma 4 31B

Embed this result▼

Paste this snippet into any page to show a live fit card.

<iframe src="https://willitrunai.com/embed/gemma-4-31b-on-gaudi-3-128gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview:

Workload

Grade

Fit

Decode

TTFT

Context

Chat

Runs well

90.2 tok/s

1170 ms

104K

Coding

Runs well

90.2 tok/s

2145 ms

104K

Agentic Coding

Runs well

90.2 tok/s

3120 ms

104K

Reasoning

Runs well

90.2 tok/s

2535 ms

104K

RAG

Runs well

90.2 tok/s

3900 ms

104K

Quantization options

How Gemma 4 31B (30.700000762939453B params) fits at each quantization level on Gaudi 3 128GB (128.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	12.0 GB	Low	A75
Q3_K_S	3	15.0 GB	Low	A76
NVFP4	4	17.2 GB	Medium	A76
Q4_K_M	4	18.7 GB	Medium	A76
Q5_K_M	5	22.1 GB	High	A76
Q6_K	6	25.2 GB	High	A76
Q8_0	8	32.8 GB	Very High	A78
F16Best for your GPU	16	62.9 GB	Maximum	A83

Model

Params

Grade

Decode

Capabilities

Devstral 2 123B Instruct

123B

37.5 tok/s

Qwen 3.5 122B A10B

122B

104.1 tok/s

Qwen 3.6 35B A3B

35B

329.1 tok/s

Qwen 3.5 35B A3B

35B

357.9 tok/s

Qwen 3 32B

32B

144.3 tok/s

Frequently asked questions

Can Gaudi 3 128GB run Gemma 4 31B?

Yes, Gaudi 3 128GB can run Gemma 4 31B with a S grade (Runs well). Expected decode speed: 90.2 tok/s.

How much VRAM does Gemma 4 31B need?

Gemma 4 31B (30.700000762939453B parameters) requires approximately 47.1 GB of memory with Q4_K_M quantization.

What is the best quantization for Gemma 4 31B?

The recommended quantization for Gemma 4 31B is Q4_K_M, which balances quality and memory efficiency.

What speed will Gemma 4 31B run at on Gaudi 3 128GB?

On Gaudi 3 128GB, Gemma 4 31B achieves approximately 90.2 tokens per second decode speed with a time-to-first-token of 2145ms using Q4_K_M quantization.

Can Gaudi 3 128GB run Gemma 4 31B for coding?

For coding workloads, Gemma 4 31B on Gaudi 3 128GB receives a S grade with 90.2 tok/s and 104K context.

What context window can Gemma 4 31B use on Gaudi 3 128GB?

On Gaudi 3 128GB, Gemma 4 31B can safely use up to 104K tokens of context. The model's official context limit is 256K, but available memory constrains the safe maximum.

What should I upgrade first if Gemma 4 31B feels slow on Gaudi 3 128GB?

Would CUDA be a better path than Gaudi 3 128GB for Gemma 4 31B?