Can Kimi Linear 48B A3B run on Gaudi 3 128GB?

YES — Runs Great

A82Great

○Estimated from fit model

Kimi Linear 48B A3B needs ~44.8 GB VRAM. Gaudi 3 128GB has 128.0 GB. With Q4_K_M quantization, expect ~89 tok/s.

Runtime: TransformersCapacity: RoomyBandwidth: HighStack: StandardBottleneck: 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) — 44.8 GB, 88.5 tok/s, Runs well

44.8 GB required128.0 GB available

35% VRAM used

Fit status

Runs well

Decode

88.5 tok/s

TTFT

2189 ms

Safe context

1.0M

Memory

44.8 GB / 128.0 GB

Memory breakdown

Weights29.3 GB

KV Cache0.9 GB

Runtime1.8 GB

Headroom12.8 GB

See how fast it feels

See how fast it feelsKimi Linear 48B A3B on Gaudi 3 128GB
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: 88.5 tok/s decode · 2.2s TTFT (warm) · 221 tok/s prefill

What limits this setup

The raw memory story may look fine, but the software ecosystem is still a constraint here.

Runtime ecosystem is narrower than CUDA

Intel GPUs can look attractive on memory per dollar, but local AI tooling, kernels, and model coverage are still broader and easier on CUDA today.

Best improvement path

Prefer CUDA if you want the path of least resistance

If your goal is maximum runtime coverage, easier troubleshooting, and better support for new local AI releases, CUDA is usually still the safer upgrade path.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	A	Runs well	88.5 tok/s	1194 ms	1.0M
Coding	A	Runs well	88.5 tok/s	2189 ms	1.0M
Agentic Coding	A	Runs well	88.5 tok/s	3183 ms	1.0M
Reasoning	A	Runs well	88.5 tok/s	2587 ms	1.0M
RAG	A	Runs well	88.5 tok/s	3979 ms	1.0M

Quantization options

How Kimi Linear 48B A3B (48B params) fits at each quantization level on Gaudi 3 128GB (128.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	18.7 GB	Low	A71
Q3_K_S	3	23.5 GB	Low	A72
NVFP4	4

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 Gaudi 3 128GB can run

Model	Params	Grade	Decode	Capabilities
👁 Mistral Devstral 2 123B Instruct	123B	S	37.5 tok/s
👁 Alibaba Qwen 3.5 122B A10B	122B	S

Frequently asked questions

See all results for Gaudi 3 128GB See all hardware for Kimi Linear 48B A3B

URL: https://willitrunai.com/can-run/kimi-linear-48b-a3b-on-gaudi-3-128gb

⇱