Can MiniMax M2.7 run on H100 NVL 188GB?

YES — Tight Fit

S90Excellent

○Estimated from fit model

MiniMax M2.7 needs ~163.8 GB VRAM. H100 NVL 188GB has 188.0 GB. With UD-IQ4_XS quantization, expect ~146 tok/s.

Runtime: llama.cppCapacity: TightBandwidth: 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) — 495.0 GB, exceeds 188.0 GB available

495.0 GB required188.0 GB available

263% VRAM needed

307.0 GB over capacity — needs offload or smaller quantization

Fit status

Too heavy

Decode

10.5 tok/s

TTFT

18400 ms

Safe context

Memory

495.0 GB / 188.0 GB

Offload

60%

Memory breakdown

Weights471.5 GB

KV Cache3.8 GB

Runtime0.9 GB

Headroom18.8 GB

See how fast it feels

With memory offload — actual speed may be lower

See how fast it feelsMiniMax M2.7 on H100 NVL 188GB
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: 10.5 tok/s decode · 18.4s TTFT (warm) · 26 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	Tight fit	146.3 tok/s	722 ms	118K
Coding	S	Tight fit	146.3 tok/s	1323 ms	118K
Agentic Coding	S	Tight fit	146.3 tok/s	1925 ms	118K
Reasoning	S	Tight fit	146.3 tok/s	1564 ms	118K
RAG	S	Tight fit	146.3 tok/s	2406 ms	118K

Quantization options

How MiniMax M2.7 (230B params) fits at each quantization level on H100 NVL 188GB (188.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	89.7 GB	Low	A83
Q3_K_S	3	112.7 GB	Low	A84
NVFP4	4	128.8 GB	Medium	A84
Q4_K_MBest for your GPU	4	140.3 GB	Medium	A84
Q5_K_M	5	165.6 GB	High	F0
Q6_K	6	188.6 GB	High	F0
Q8_0	8	246.1 GB	Very High	F0
F16	16	471.5 GB	Maximum	F0

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 H100 NVL 188GB can run

Model	Params	Grade	Decode	Capabilities
👁 DeepSeek DeepSeek V4 Flash	284B	S	136.1 tok/s
👁 Alibaba Qwen 3 235B A22B	235B	S	128.6 tok/s

Frequently asked questions

See all results for H100 NVL 188GB See all hardware for MiniMax M2.7

URL: https://willitrunai.com/can-run/minimax-m2-7-on-h100-nvl-188gb

⇱ MiniMax M2.7 on H100 NVL 188GB? TIGHT FIT