Can Kimi Linear 48B A3B run on NVIDIA H800 80GB?

YES — Runs Great

A84Great

Estimated from fit model

Kimi Linear 48B A3B needs ~40.6 GB VRAM. NVIDIA H800 80GB has 80.0 GB. With Q4_K_M quantization, expect ~66 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) — 40.6 GB, 66.4 tok/s, Runs well

40.6 GB required80.0 GB available

51% VRAM used

Fit status

Runs well

Decode

66.4 tok/s

TTFT

2916 ms

Safe context

696K

Memory

40.6 GB / 80.0 GB

Memory breakdown

Weights29.3 GB

KV Cache0.9 GB

Runtime2.4 GB

Headroom8.0 GB

See how fast it feels

See how fast it feelsKimi Linear 48B A3B on NVIDIA H800 80GB
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: 66.4 tok/s decode · 2.9s TTFT (warm) · 166 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	66.4 tok/s	1591 ms	696K
Coding	A	Runs well	66.4 tok/s	2916 ms	696K
Agentic Coding	A	Runs well	66.4 tok/s	4241 ms	696K
Reasoning	A	Runs well	66.4 tok/s	3446 ms	696K
RAG	A	Runs well	66.4 tok/s	5302 ms	696K

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 H800 80GB (80.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	18.7 GB	Low	A74
Q3_K_S	3	23.5 GB	Low	A75
NVFP4	4	26.9 GB	Medium	A76
Q4_K_M	4	29.3 GB	Medium	A76
Q5_K_M	5	34.6 GB	High	A78
Q6_K	6	39.4 GB	High	A79
Q8_0Best for your GPU	8	51.4 GB	Very High	A80
F16	16	98.4 GB	Maximum	F0

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 H800 80GB can run

Model	Params	Grade	Decode
Qwen 2.5 VL 72B	72B	S	48.1 tok/s
Qwen3-Coder-Next	80B	S	103.9 tok/s
Llama 3.3 70B	70B	S	49.5 tok/s

Frequently asked questions

Can NVIDIA H800 80GB run Kimi Linear 48B A3B?

Yes, NVIDIA H800 80GB can run Kimi Linear 48B A3B with a A grade (Runs well). Expected decode speed: 66.4 tok/s.

How much VRAM does Kimi Linear 48B A3B need?

Kimi Linear 48B A3B (48B parameters) requires approximately 40.6 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 H800 80GB?

On NVIDIA H800 80GB, Kimi Linear 48B A3B achieves approximately 66.4 tokens per second decode speed with a time-to-first-token of 2916ms using Q4_K_M quantization.

Can NVIDIA H800 80GB run Kimi Linear 48B A3B for coding?

For coding workloads, Kimi Linear 48B A3B on NVIDIA H800 80GB receives a A grade with 66.4 tok/s and 696K context.

What context window can Kimi Linear 48B A3B use on NVIDIA H800 80GB?

On NVIDIA H800 80GB, Kimi Linear 48B A3B can safely use up to 696K tokens of context. The model's official context limit is 1.0M, but available memory constrains the safe maximum.

See all results for NVIDIA H800 80GB 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-h800-80gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview:

Workload

Grade

Fit

Decode

TTFT

Context

Chat

Runs well

66.4 tok/s

1591 ms

696K

Coding

Runs well

66.4 tok/s

2916 ms

696K

Agentic Coding

Runs well

66.4 tok/s

4241 ms

696K

Reasoning

Runs well

66.4 tok/s

3446 ms

696K

RAG

Runs well

66.4 tok/s

5302 ms

696K

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

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

Quantization options

How Kimi Linear 48B A3B (48B params) fits at each quantization level on NVIDIA H800 80GB (80.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	18.7 GB	Low	A74
Q3_K_S	3	23.5 GB	Low	A75
NVFP4	4	26.9 GB	Medium	A76
Q4_K_M	4	29.3 GB	Medium	A76
Q5_K_M	5	34.6 GB	High	A78
Q6_K	6	39.4 GB	High	A79
Q8_0Best for your GPU	8	51.4 GB	Very High	A80
F16	16	98.4 GB	Maximum	F0

Model

Params

Grade

Decode

Capabilities

Qwen 2.5 VL 72B

72B

48.1 tok/s

Qwen3-Coder-Next

80B

103.9 tok/s

Llama 3.3 70B

70B

49.5 tok/s

Frequently asked questions

Can NVIDIA H800 80GB run Kimi Linear 48B A3B?

Yes, NVIDIA H800 80GB can run Kimi Linear 48B A3B with a A grade (Runs well). Expected decode speed: 66.4 tok/s.

How much VRAM does Kimi Linear 48B A3B need?

Kimi Linear 48B A3B (48B parameters) requires approximately 40.6 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 H800 80GB?

On NVIDIA H800 80GB, Kimi Linear 48B A3B achieves approximately 66.4 tokens per second decode speed with a time-to-first-token of 2916ms using Q4_K_M quantization.

Can NVIDIA H800 80GB run Kimi Linear 48B A3B for coding?

For coding workloads, Kimi Linear 48B A3B on NVIDIA H800 80GB receives a A grade with 66.4 tok/s and 696K context.

What context window can Kimi Linear 48B A3B use on NVIDIA H800 80GB?

On NVIDIA H800 80GB, Kimi Linear 48B A3B can safely use up to 696K tokens of context. The model's official context limit is 1.0M, but available memory constrains the safe maximum.