Can Kimi Linear 48B A3B run on NVIDIA H200 141GB?

YES — Runs Great

A81Great

○Estimated from fit model

Kimi Linear 48B A3B needs ~46.7 GB VRAM. NVIDIA H200 141GB has 141.0 GB. With Q4_K_M quantization, expect ~110 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) — 46.7 GB, 110.2 tok/s, Runs well

46.7 GB required141.0 GB available

33% VRAM used

Fit status

Runs well

Decode

110.2 tok/s

TTFT

1757 ms

Safe context

1.0M

Memory

46.7 GB / 141.0 GB

Memory breakdown

Weights29.3 GB

KV Cache0.9 GB

Runtime2.4 GB

Headroom14.1 GB

See how fast it feels

See how fast it feelsKimi Linear 48B A3B on NVIDIA H200 141GB
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: 110.2 tok/s decode · 1.8s TTFT (warm) · 275 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	110.2 tok/s	959 ms	1.0M
Coding	A	Runs well	110.2 tok/s	1757 ms	1.0M
Agentic Coding	A	Runs well	110.2 tok/s	2556 ms	1.0M
Reasoning	A	Runs well	110.2 tok/s	2077 ms	1.0M
RAG	A	Runs well	110.2 tok/s	3195 ms	1.0M

Quantization options

How Kimi Linear 48B A3B (48B params) fits at each quantization level on NVIDIA H200 141GB (141.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	18.7 GB	Low	A71
Q3_K_S	3	23.5 GB	Low	A71
NVFP4	4	26.9 GB	Medium	A72
Q4_K_M	4	29.3 GB	Medium	A72
Q5_K_M	5	34.6 GB	High	A73
Q6_K	6	39.4 GB	High	A74
Q8_0	8	51.4 GB	Very High	A76
F16Best for your GPU	16	98.4 GB	Maximum	A80

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 NVIDIA H200 141GB can run

Model	Params	Grade	Decode
👁 Mistral Devstral 2 123B Instruct	123B	S	46.8 tok/s
👁 Alibaba Qwen 3.5 122B A10B	122B	S	88.7 tok/s
👁 Mistral Mistral Small 4 119B	119B	S	96.2 tok/s
👁 OpenAI GPT-OSS 120B	117B	S	49.2 tok/s
👁 Cohere Command A 111B	111B	S	52 tok/s

Frequently asked questions

See all results for NVIDIA H200 141GB See all hardware for Kimi Linear 48B A3B

URL: https://willitrunai.com/can-run/kimi-linear-48b-a3b-on-h200-141gb

⇱ Kimi Linear 48B A3B on NVIDIA H200 141GB? YES