Can Gemma 4 12B run on Gaudi 3 128GB?

YES — Runs Great

A78Great

Estimated from fit model

Gemma 4 12B needs ~26.9 GB VRAM. Gaudi 3 128GB has 128.0 GB. With Q4_K_M quantization, expect ~168 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) — 26.9 GB, 168.0 tok/s, Runs well

26.9 GB required128.0 GB available

21% VRAM used

Fit status

Runs well

Decode

168.0 tok/s

TTFT

1152 ms

Safe context

262K

Memory

26.9 GB / 128.0 GB

Memory breakdown

Weights7.3 GB

KV Cache5.9 GB

Runtime0.9 GB

Headroom12.8 GB

See how fast it feels

See how fast it feelsGemma 4 12B 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: 168.0 tok/s decode · 1.2s TTFT (warm) · 420 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	A	Runs well	168.0 tok/s	629 ms	262K
Coding	A	Runs well	168.0 tok/s	1152 ms	262K
Agentic Coding	A	Runs well	168.0 tok/s	1676 ms	262K
Reasoning	A	Runs well	168.0 tok/s	1362 ms	262K
RAG	A	Runs well	168.0 tok/s	2095 ms	262K

Inference speed

Gemma 4 12B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Gemma 4 12B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~168 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.

GPU / Mac	Memory	Quant	Speed (tok/s)	Fits?
RTX 5090 32GB	32 GB	Q4_K_M	168.0	Fits
RTX 4090 24GB	24 GB	Q4_K_M	109.9	Fits
RX 7900 XTX 24GB	24 GB	Q4_K_M	99.1	Fits
RTX 3090 24GB	24 GB	Q4_K_M	94.0	Fits
RTX 4080 Super 16GB	16 GB	Q4_K_M	87.6	Offloads
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	60.5	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	50.4	Fits
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	47.8	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	43.4	Fits
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	34.4	Fits
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	32.9	Fits
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	31.6	Fits
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	26.5	Fits
RTX 4070 12GB	12 GB	Q4_K_M	23.5	Too big
RTX 3060 12GB	12 GB	Q4_K_M	14.8	Too big
RTX 4060 8GB	8 GB	Q4_K_M	5.5	Too big

Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.

Quantization options

How Gemma 4 12B (12B params) fits at each quantization level on Gaudi 3 128GB (128.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	4.7 GB	Low	B70
Q3_K_S	3	5.9 GB	Low	B70
NVFP4	4	6.7 GB	Medium	B70
Q4_K_M	4	7.3 GB	Medium	B70
Q5_K_M	5	8.6 GB	High	B70
Q6_K	6	9.8 GB	High	B70
Q8_0	8	12.8 GB	Very High	B70
F16Best for your GPU	16	24.6 GB	Maximum	A71

Get started

Copy-paste commands to run Gemma 4 12B on your machine.

Run

lms load gemma-4-12B-it && lms server start

Your hardware

More models your Gaudi 3 128GB can run

Model	Params	Grade	Decode
Devstral 2 123B Instruct	123B	S	37.5 tok/s
Qwen3-Coder 30B A3B Instruct	30.5B	S	391.6 tok/s
Qwen 3.5 27B	27B	S	169.8 tok/s
Qwen 3.6 27B	27B	S	105.9 tok/s
Qwen 3.5 122B A10B	122B	S	104.1 tok/s

Frequently asked questions

Can Gaudi 3 128GB run Gemma 4 12B?

Yes, Gaudi 3 128GB can run Gemma 4 12B with a A grade (Runs well). Expected decode speed: 168.0 tok/s.

How much VRAM does Gemma 4 12B need?

Gemma 4 12B (12B parameters) requires approximately 26.9 GB of memory with Q4_K_M quantization.

What is the best quantization for Gemma 4 12B?

The recommended quantization for Gemma 4 12B is Q4_K_M, which balances quality and memory efficiency.

What speed will Gemma 4 12B run at on Gaudi 3 128GB?

On Gaudi 3 128GB, Gemma 4 12B achieves approximately 168.0 tokens per second decode speed with a time-to-first-token of 1152ms using Q4_K_M quantization.

Can Gaudi 3 128GB run Gemma 4 12B for coding?

For coding workloads, Gemma 4 12B on Gaudi 3 128GB receives a A grade with 168.0 tok/s and 262K context.

What context window can Gemma 4 12B use on Gaudi 3 128GB?

On Gaudi 3 128GB, Gemma 4 12B can safely use up to 262K tokens of context. The model's official context limit is 262K, but available memory constrains the safe maximum.

What should I upgrade first if Gemma 4 12B 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 12B?

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 12B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/gemma-4-12b-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: