Can Kimi Linear 48B A3B run on AMD Instinct MI350X 288GB?

YES — Runs Great

A79Great

○Estimated from fit model

Kimi Linear 48B A3B needs ~61.4 GB VRAM. AMD Instinct MI350X 288GB has 288.0 GB. With Q4_K_M quantization, expect ~160 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) — 61.4 GB, 159.6 tok/s, Runs well

61.4 GB required288.0 GB available

21% VRAM used

Fit status

Runs well

Decode

159.6 tok/s

TTFT

1213 ms

Safe context

1.0M

Memory

61.4 GB / 288.0 GB

Memory breakdown

Weights29.3 GB

KV Cache0.9 GB

Runtime2.4 GB

Headroom28.8 GB

See how fast it feels

See how fast it feelsKimi Linear 48B A3B on AMD Instinct MI350X 288GB
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: 159.6 tok/s decode · 1.2s TTFT (warm) · 399 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	159.6 tok/s	662 ms	1.0M
Coding	A	Runs well	159.6 tok/s	1213 ms	1.0M
Agentic Coding	A	Runs well	159.6 tok/s	1765 ms	1.0M
Reasoning	A	Runs well	159.6 tok/s	1434 ms	1.0M
RAG	A	Runs well	159.6 tok/s	2206 ms	1.0M

Quantization options

How Kimi Linear 48B A3B (48B params) fits at each quantization level on AMD Instinct MI350X 288GB (288.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	18.7 GB	Low	B69
Q3_K_S	3	23.5 GB	Low	B69
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 AMD Instinct MI350X 288GB can run

Model	Params	Grade	Decode	Capabilities
👁 Mistral Devstral 2 123B Instruct	123B	S	67.7 tok/s
👁 Alibaba Qwen 3.5 122B A10B	122B	S

Frequently asked questions

See all results for AMD Instinct MI350X 288GB See all hardware for Kimi Linear 48B A3B

URL: https://willitrunai.com/can-run/kimi-linear-48b-a3b-on-instinct-mi350x-288gb

⇱