Can Kimi Linear 48B A3B run on H100 NVL 188GB?

YES — Runs Great

A80Great

○Estimated from fit model

Kimi Linear 48B A3B needs ~51.4 GB VRAM. H100 NVL 188GB has 188.0 GB. With Q4_K_M quantization, expect ~173 tok/s.

Runtime: vLLMCapacity: RoomyBandwidth: HighStack: OptimizedBottleneck: 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) — 51.4 GB, 172.6 tok/s, Runs well

51.4 GB required188.0 GB available

27% VRAM used

Fit status

Runs well

Decode

172.6 tok/s

TTFT

1122 ms

Safe context

1.0M

Memory

51.4 GB / 188.0 GB

Memory breakdown

Weights29.3 GB

KV Cache0.9 GB

Runtime2.4 GB

Headroom18.8 GB

See how fast it feels

See how fast it feelsKimi Linear 48B A3B 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: 172.6 tok/s decode · 1.1s TTFT (warm) · 432 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	172.6 tok/s	612 ms	1.0M
Coding	A	Runs well	172.6 tok/s	1122 ms	1.0M
Agentic Coding	A	Runs well	172.6 tok/s	1631 ms	1.0M
Reasoning	A	Runs well	172.6 tok/s	1325 ms	1.0M
RAG	A	Runs well	172.6 tok/s	2039 ms	1.0M

Quantization options

How Kimi Linear 48B A3B (48B params) fits at each quantization level on H100 NVL 188GB (188.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	18.7 GB	Low	B70
Q3_K_S	3	23.5 GB	Low	A70
NVFP4	4	26.9 GB	Medium	A71
Q4_K_M	4	29.3 GB	Medium	A71
Q5_K_M	5	34.6 GB	High	A72
Q6_K	6	39.4 GB	High	A72
Q8_0	8	51.4 GB	Very High	A74
F16Best for your GPU	16	98.4 GB	Maximum	A79

Get started

Copy-paste commands to run Kimi Linear 48B A3B on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
 --hf-repo "moonshotai/Kimi-Linear-48B-A3B-Instruct" \
 --hf-file "Kimi-Linear-48B-A3B-Instruct-Q4_K_M.gguf" \
 -c 4096 -ngl 99

Your hardware

More models your H100 NVL 188GB can run

Model	Params	Grade	Decode
👁 Mistral Devstral 2 123B Instruct	123B	S	73.3 tok/s
👁 Alibaba Qwen 3.5 122B A10B	122B	S	139 tok/s
👁 Mistral Mistral Small 4 119B	119B	S	150.7 tok/s
👁 OpenAI GPT-OSS 120B	117B	S	77 tok/s
👁 Cohere Command A 111B	111B	S	81.5 tok/s

Frequently asked questions

See all results for H100 NVL 188GB See all hardware for Kimi Linear 48B A3B

URL: https://willitrunai.com/can-run/kimi-linear-48b-a3b-on-h100-nvl-188gb

⇱ Kimi Linear 48B A3B on H100 NVL 188GB? YES