Can Gemma 4 26B A4B run on NVIDIA H100 80GB?

YES — Runs Great

A84Great

○Estimated from fit model

Gemma 4 26B A4B needs ~28.2 GB VRAM. NVIDIA H100 80GB has 80.0 GB. With Q4_K_M quantization, expect ~457 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) — 28.2 GB, 457.0 tok/s, Runs well

28.2 GB required80.0 GB available

35% VRAM used

Fit status

Runs well

Decode

457.0 tok/s

TTFT

424 ms

Safe context

242K

Memory

28.2 GB / 80.0 GB

Memory breakdown

Weights15.4 GB

KV Cache3.7 GB

Runtime1.2 GB

Headroom8.0 GB

See how fast it feels

See how fast it feelsGemma 4 26B A4B on NVIDIA H100 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: 457.0 tok/s decode · 424ms TTFT (warm) · 1142 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	457.0 tok/s	350 ms	242K
Coding	A	Runs well	457.0 tok/s	424 ms	242K
Agentic Coding	S	Runs well	457.0 tok/s	616 ms	242K
Reasoning	A	Runs well	457.0 tok/s	501 ms	242K
RAG	S	Runs well	457.0 tok/s	770 ms	242K

Quantization options

How Gemma 4 26B A4B (25.200000762939453B params) fits at each quantization level on NVIDIA H100 80GB (80.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	9.8 GB	Low	A75
Q3_K_S	3	12.3 GB	Low	A76
NVFP4	4	14.1 GB	Medium	A76
Q4_K_M	4	15.4 GB	Medium	A76
Q5_K_M	5	18.1 GB	High	A76
Q6_K	6	20.7 GB	High	A77
Q8_0	8	27.0 GB	Very High	A78
F16Best for your GPU	16	51.7 GB	Maximum	A83

Get started

Copy-paste commands to run Gemma 4 26B A4B on your machine.

Run

ollama run gemma4:26b

Your hardware

More models your NVIDIA H100 80GB can run

Model	Params	Grade	Decode
👁 Mistral Devstral 2 123B Instruct	123B	A	28.9 tok/s
👁 Alibaba Qwen3-Coder 30B A3B Instruct	30.5B	S	425.5 tok/s
👁 Alibaba Qwen 3.5 27B	27B	S	184.5 tok/s
👁 Alibaba Qwen 3.6 27B	27B	S	185.1 tok/s
👁 Alibaba Qwen 3.5 122B A10B	122B	S	85.5 tok/s

Frequently asked questions

See all results for NVIDIA H100 80GB See all hardware for Gemma 4 26B A4B

URL: https://willitrunai.com/can-run/gemma-4-26b-a4b-on-h100-80gb

⇱ Gemma 4 26B A4B on NVIDIA H100 80GB? YES