Can Kimi K2.5 run on NVIDIA GB200 192GB?

NO — Won't Fit

F0Won't run

○Estimated from fit model

Kimi K2.5 needs ~639.0 GB but NVIDIA GB200 192GB only has 192.0 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) — 639.0 GB, exceeds 192.0 GB available

639.0 GB required192.0 GB available

333% VRAM needed

447.0 GB over capacity — needs offload or smaller quantization

Fit status

Too heavy

Decode

4.1 tok/s

TTFT

46691 ms

Safe context

Memory

639.0 GB / 192.0 GB

Offload

70%

Memory breakdown

Weights610.0 GB

KV Cache7.4 GB

Runtime2.4 GB

Headroom19.2 GB

See how fast it feels

With memory offload — actual speed may be lower

See how fast it feelsKimi K2.5 on NVIDIA GB200 192GB
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: 4.1 tok/s decode · 46.7s TTFT (warm) · 10 tok/s prefill

What limits this setup

Usable VRAM is the main blocker for this model.

Not enough usable memory

The model needs 639.0 GB, but this setup only exposes 192.0 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	4.1 tok/s	25468 ms	4K
Coding	F	Too heavy	4.1 tok/s	46691 ms	4K
Agentic Coding	F	Too heavy	4.1 tok/s	67915 ms	4K
Reasoning	F	Too heavy	4.1 tok/s	55181 ms	4K
RAG	F	Too heavy	4.1 tok/s	84893 ms	4K

Quantization options

How Kimi K2.5 (1000B params) fits at each quantization level on NVIDIA GB200 192GB (192.0 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

Frequently asked questions

See all results for NVIDIA GB200 192GB See all hardware for Kimi K2.5

URL: https://willitrunai.com/can-run/kimi-k2-5-on-gb200-192gb

⇱