Can Kimi K2.5 run on H100 NVL 188GB?

NO — Won't Fit

F0Won't run

Estimated from fit model

Kimi K2.5 needs ~638.6 GB but H100 NVL 188GB only has 188.0 GB. Try a smaller quantization or lighter model.

Runtime: vLLMCapacity: No fitBandwidth: HighStack: OptimizedBottleneck: Memory capacity

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) — 638.6 GB, exceeds 188.0 GB available

638.6 GB required188.0 GB available

340% VRAM needed

450.6 GB over capacity — needs offload or smaller quantization

Fit status

Too heavy

Decode

2.8 tok/s

TTFT

68975 ms

Safe context

Memory

638.6 GB / 188.0 GB

Offload

70%

Memory breakdown

Weights610.0 GB

KV Cache7.4 GB

Runtime2.4 GB

Headroom18.8 GB

See how fast it feels

With memory offload — actual speed may be lower

See how fast it feelsKimi K2.5 on H100 NVL 188GB
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: 2.8 tok/s decode · 69.0s TTFT (warm) · 7 tok/s prefill

What limits this setup

Usable VRAM is the main blocker for this model.

Not enough usable memory

The model needs 638.6 GB, but this setup only exposes 188.0 GB of usable VRAM.

Best improvement path

Add more VRAM headroom

The first useful upgrade is more dedicated VRAM so you can fit the model without shrinking context or dropping to a much lower quant.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	F	Too heavy	2.8 tok/s	37623 ms	4K
Coding	F	Too heavy	2.8 tok/s	68975 ms	4K
Agentic Coding	F	Too heavy	2.8 tok/s	100328 ms	4K
Reasoning	F	Too heavy	2.8 tok/s	81516 ms	4K
RAG	F	Too heavy	2.8 tok/s	125410 ms	4K

Quantization options

How Kimi K2.5 (1000B params) fits at each quantization level on H100 NVL 188GB (188.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	390.0 GB	Low	F0
Q3_K_S	3	490.0 GB	Low	F0
NVFP4	4	560.0 GB	Medium	F0
Q4_K_M	4	610.0 GB	Medium	F0
Q5_K_M	5	720.0 GB	High	F0
Q6_K	6	820.0 GB	High	F0
Q8_0	8	1070.0 GB	Very High	F0
F16	16	2050.0 GB	Maximum	F0

Frequently asked questions

Can H100 NVL 188GB run Kimi K2.5?

No, Kimi K2.5 requires more memory than H100 NVL 188GB provides.

How much VRAM does Kimi K2.5 need?

Kimi K2.5 (1000B parameters) requires approximately 638.6 GB of memory with Q4_K_M quantization.

What is the best quantization for Kimi K2.5?

The recommended quantization for Kimi K2.5 is Q4_K_M, which balances quality and memory efficiency.

What speed will Kimi K2.5 run at on H100 NVL 188GB?

On H100 NVL 188GB, Kimi K2.5 achieves approximately 2.8 tokens per second decode speed with a time-to-first-token of 68975ms using Q4_K_M quantization.

Can H100 NVL 188GB run Kimi K2.5 for coding?

For coding workloads, Kimi K2.5 on H100 NVL 188GB receives a F grade with 2.8 tok/s and 4K context.

What context window can Kimi K2.5 use on H100 NVL 188GB?

On H100 NVL 188GB, Kimi K2.5 can safely use up to 4K tokens of context. The model's official context limit is 256K, but available memory constrains the safe maximum.

What should I upgrade first if Kimi K2.5 feels slow on H100 NVL 188GB?

Add more VRAM headroom. The first useful upgrade is more dedicated VRAM so you can fit the model without shrinking context or dropping to a much lower quant.

See all results for H100 NVL 188GB See all hardware for Kimi K2.5

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/kimi-k2-5-on-h100-nvl-188gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: