Can MiniMax M2.7 run on AMD Instinct MI350X 288GB?

YES — Runs Great

S91Excellent

○Estimated from fit model

MiniMax M2.7 needs ~173.8 GB VRAM. AMD Instinct MI350X 288GB has 288.0 GB. With UD-IQ4_XS quantization, expect ~135 tok/s.

Runtime: llama.cppCapacity: 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

F16 (Maximum quality) — 505.0 GB, exceeds 288.0 GB available

505.0 GB required288.0 GB available

175% VRAM needed

217.0 GB over capacity — needs offload or smaller quantization

Fit status

Too heavy

Decode

13.0 tok/s

TTFT

14945 ms

Safe context

Memory

505.0 GB / 288.0 GB

Offload

40%

Memory breakdown

Weights471.5 GB

KV Cache3.8 GB

Runtime0.9 GB

Headroom28.8 GB

See how fast it feels

With memory offload — actual speed may be lower

See how fast it feelsMiniMax M2.7 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: 13.0 tok/s decode · 14.9s TTFT (warm) · 32 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	S	Runs well	135.2 tok/s	781 ms	205K
Coding	S	Runs well	135.2 tok/s	1432 ms	205K
Agentic Coding	S	Runs well	135.2 tok/s	2083 ms	205K
Reasoning	S	Runs well	135.2 tok/s	1692 ms	205K
RAG	S	Runs well	135.2 tok/s	2603 ms	205K

Quantization options

How MiniMax M2.7 (230B params) fits at each quantization level on AMD Instinct MI350X 288GB (288.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	89.7 GB	Low	A79
Q3_K_S	3	112.7 GB	Low	A81
NVFP4	4

Get started

Copy-paste commands to run MiniMax M2.7 on your machine.

Run

lms load MiniMax-M2.7 && lms server start

Your hardware

More models your AMD Instinct MI350X 288GB can run

Model	Params	Grade	Decode	Capabilities
👁 Alibaba Qwen 3.5 397B A17B	397B	S	78.9 tok/s
👁 DeepSeek DeepSeek V4 Flash	284B	S

Frequently asked questions

See all results for AMD Instinct MI350X 288GB See all hardware for MiniMax M2.7

URL: https://willitrunai.com/can-run/minimax-m2-7-on-instinct-mi350x-288gb

⇱