Can Gemma 4 12B run on NVIDIA H100 PCIe 80GB?

YES — Runs Great

A79Great

Estimated from fit model

Gemma 4 12B needs ~22.4 GB VRAM. NVIDIA H100 PCIe 80GB has 80.0 GB. With Q4_K_M quantization, expect ~168 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) — 22.4 GB, 168.0 tok/s, Runs well

22.4 GB required80.0 GB available

28% VRAM used

Fit status

Runs well

Decode

168.0 tok/s

TTFT

1152 ms

Safe context

173K

Memory

22.4 GB / 80.0 GB

Memory breakdown

Weights7.3 GB

KV Cache5.9 GB

Runtime1.2 GB

Headroom8.0 GB

See how fast it feels

See how fast it feelsGemma 4 12B on NVIDIA H100 PCIe 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: 168.0 tok/s decode · 1.2s TTFT (warm) · 420 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	168.0 tok/s	629 ms	173K
Coding	A	Runs well	168.0 tok/s	1152 ms	173K
Agentic Coding	A	Runs well	168.0 tok/s	1676 ms	173K
Reasoning	A	Runs well	168.0 tok/s	1362 ms	173K
RAG	A	Runs well	168.0 tok/s	2095 ms	173K

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 NVIDIA H100 PCIe 80GB (80.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	4.7 GB	Low	A71
Q3_K_S	3	5.9 GB	Low	A71
NVFP4	4	6.7 GB	Medium	A71
Q4_K_M	4	7.3 GB	Medium	A71
Q5_K_M	5	8.6 GB	High	A71
Q6_K	6	9.8 GB	High	A72
Q8_0	8	12.8 GB	Very High	A72
F16Best for your GPU	16	24.6 GB	Maximum	A74

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 NVIDIA H100 PCIe 80GB can run

Model	Params	Grade	Decode
Devstral 2 123B Instruct	123B	A	14.8 tok/s
Qwen3-Coder 30B A3B Instruct	30.5B	S	254 tok/s
Qwen 3.5 27B	27B	S	110.2 tok/s
Qwen 3.6 27B	27B	S	110.5 tok/s
Qwen 3.5 122B A10B	122B	A	44.5 tok/s

Frequently asked questions

Can NVIDIA H100 PCIe 80GB run Gemma 4 12B?

Yes, NVIDIA H100 PCIe 80GB 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 22.4 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 NVIDIA H100 PCIe 80GB?

On NVIDIA H100 PCIe 80GB, 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 NVIDIA H100 PCIe 80GB run Gemma 4 12B for coding?

For coding workloads, Gemma 4 12B on NVIDIA H100 PCIe 80GB receives a A grade with 168.0 tok/s and 173K context.

What context window can Gemma 4 12B use on NVIDIA H100 PCIe 80GB?

On NVIDIA H100 PCIe 80GB, Gemma 4 12B can safely use up to 173K tokens of context. The model's official context limit is 262K, but available memory constrains the safe maximum.

See all results for NVIDIA H100 PCIe 80GB 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-h100-pcie-80gb" 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

168.0 tok/s

629 ms

173K

Coding

Runs well

168.0 tok/s

1152 ms

173K

Agentic Coding

Runs well

168.0 tok/s

1676 ms

173K

Reasoning

Runs well

168.0 tok/s

1362 ms

173K

RAG

Runs well

168.0 tok/s

2095 ms

173K

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

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

Quantization options

How Gemma 4 12B (12B params) fits at each quantization level on NVIDIA H100 PCIe 80GB (80.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	4.7 GB	Low	A71
Q3_K_S	3	5.9 GB	Low	A71
NVFP4	4	6.7 GB	Medium	A71
Q4_K_M	4	7.3 GB	Medium	A71
Q5_K_M	5	8.6 GB	High	A71
Q6_K	6	9.8 GB	High	A72
Q8_0	8	12.8 GB	Very High	A72
F16Best for your GPU	16	24.6 GB	Maximum	A74

Model

Params

Grade

Decode

Capabilities

Devstral 2 123B Instruct

123B

14.8 tok/s

Qwen3-Coder 30B A3B Instruct

30.5B

254 tok/s

Qwen 3.5 27B

27B

110.2 tok/s

Qwen 3.6 27B

27B

110.5 tok/s

Qwen 3.5 122B A10B

122B

44.5 tok/s

Frequently asked questions

Can NVIDIA H100 PCIe 80GB run Gemma 4 12B?

Yes, NVIDIA H100 PCIe 80GB 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 22.4 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 NVIDIA H100 PCIe 80GB?

On NVIDIA H100 PCIe 80GB, 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 NVIDIA H100 PCIe 80GB run Gemma 4 12B for coding?

For coding workloads, Gemma 4 12B on NVIDIA H100 PCIe 80GB receives a A grade with 168.0 tok/s and 173K context.

What context window can Gemma 4 12B use on NVIDIA H100 PCIe 80GB?

On NVIDIA H100 PCIe 80GB, Gemma 4 12B can safely use up to 173K tokens of context. The model's official context limit is 262K, but available memory constrains the safe maximum.