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

YES — Runs Great

A81Great

Estimated from fit model

Kimi Linear 48B A3B needs ~46.7 GB VRAM. NVIDIA H200 PCIe 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 PCIe 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

Inference speed

Kimi Linear 48B A3B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Kimi Linear 48B A3B at Q4_K_M across popular GPUs and Apple Silicon, including multi-GPU rigs, using the fastest local runtime per device. Fastest is 2× RX 7900 XTX 24GB at ~40 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.

GPU / Mac	Memory	Quant	Speed (tok/s)	Fits?
2× RX 7900 XTX 24GB	48 GB	Q4_K_M	40.1	Fits
2× RTX 4090 24GB	48 GB	Q4_K_M	29.3	Fits
RTX 5090 32GB	32 GB	Q4_K_M	25.8	Heavy offload
2× RTX 3090 24GB	48 GB	Q4_K_M	25.1	Fits
4× RTX 3060 12GB	48 GB	Q4_K_M	22.1	Fits
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	21.1	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	21.1	Tight
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	19.0	Fits
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	15.8	Fits
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	15.0	Fits
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	10.6	Offloads
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	8.2	Tight
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	7.5	Tight
RTX 4090 24GB	24 GB	Q4_K_M	7.1	Too big
RX 7900 XTX 24GB	24 GB	Q4_K_M	6.4	Too big
RTX 3090 24GB	24 GB	Q4_K_M	6.1	Too big
RTX 4080 Super 16GB	16 GB	Q4_K_M	2.5	Too big
RTX 4070 12GB	12 GB	Q4_K_M	2.0	Too big
RTX 3060 12GB	12 GB	Q4_K_M	2.0	Too big
RTX 4060 8GB	8 GB	Q4_K_M	2.0	Too big

Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.

Quantization options

How Kimi Linear 48B A3B (48B params) fits at each quantization level on NVIDIA H200 PCIe 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 PCIe 141GB can run

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

Frequently asked questions

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

Yes, NVIDIA H200 PCIe 141GB can run Kimi Linear 48B A3B with a A grade (Runs well). Expected decode speed: 110.2 tok/s.

How much VRAM does Kimi Linear 48B A3B need?

Kimi Linear 48B A3B (48B parameters) requires approximately 46.7 GB of memory with Q4_K_M quantization.

What is the best quantization for Kimi Linear 48B A3B?

The recommended quantization for Kimi Linear 48B A3B is Q4_K_M, which balances quality and memory efficiency.

What speed will Kimi Linear 48B A3B run at on NVIDIA H200 PCIe 141GB?

On NVIDIA H200 PCIe 141GB, Kimi Linear 48B A3B achieves approximately 110.2 tokens per second decode speed with a time-to-first-token of 1757ms using Q4_K_M quantization.

Can NVIDIA H200 PCIe 141GB run Kimi Linear 48B A3B for coding?

For coding workloads, Kimi Linear 48B A3B on NVIDIA H200 PCIe 141GB receives a A grade with 110.2 tok/s and 1.0M context.

What context window can Kimi Linear 48B A3B use on NVIDIA H200 PCIe 141GB?

On NVIDIA H200 PCIe 141GB, Kimi Linear 48B A3B can safely use up to 1.0M tokens of context. The model's official context limit is 1.0M, but available memory constrains the safe maximum.

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

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/kimi-linear-48b-a3b-on-h200-pcie-141gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: