Can MiniMax M2.7 run on NVIDIA H200 141GB?

BARELY — Tight on Memory

A79Great

Estimated from fit model

MiniMax M2.7 needs ~159.1 GB VRAM. NVIDIA H200 141GB has 141.0 GB. With UD-IQ4_XS quantization, expect ~65 tok/s.

Runtime: llama.cppCapacity: OffloadBandwidth: HighStack: StandardBottleneck: Host offload

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) — 490.3 GB, exceeds 141.0 GB available

490.3 GB required141.0 GB available

348% VRAM needed

349.3 GB over capacity — needs offload or smaller quantization

Fit status

Too heavy

Decode

5.8 tok/s

TTFT

33188 ms

Safe context

Memory

490.3 GB / 141.0 GB

Offload

70%

Memory breakdown

Weights471.5 GB

KV Cache3.8 GB

Runtime0.9 GB

Headroom14.1 GB

See how fast it feels

With memory offload — actual speed may be lower

See how fast it feelsMiniMax M2.7 on NVIDIA H200 141GB
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: 5.8 tok/s decode · 33.2s TTFT (warm) · 15 tok/s prefill

What limits this setup

It fits through host-memory offload, and offload is the main reason performance drops.

CPU or host-memory offload is active

About 10% of the working set spills out of accelerator memory, which usually hurts latency and sustained decode throughput.

Very little memory headroom

You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.

Best improvement path

Remove offload with more accelerator memory

Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.

Buy headroom, not only minimum fit

A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.

Increase host RAM if you keep offloading

This setup may need roughly 15.9 GB of extra host RAM just for the offloaded portion, before OS and other tools.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	A	Very compromised (needs ~14.5 GB host RAM)	66.6 tok/s	1587 ms	4K
Coding	A	Very compromised (needs ~15.9 GB host RAM)	65.2 tok/s	2967 ms	4K
Agentic Coding	A	Very compromised (needs ~18.8 GB host RAM)	62.8 tok/s	4486 ms	4K
Reasoning	A	Very compromised (needs ~15.9 GB host RAM)	65.2 tok/s	3507 ms	4K
RAG	A	Very compromised (needs ~18.8 GB host RAM)	62.8 tok/s	5608 ms	4K

Inference speed

MiniMax M2.7 inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for MiniMax M2.7 at UD-IQ4_XS across popular GPUs and Apple Silicon, including multi-GPU rigs, using the fastest local runtime per device. Fastest is Mac Studio M3 Ultra 256GB at ~20 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?
Mac Studio M3 Ultra 256GB	256 GB	UD-IQ4_XS	20.0	Tight
Mac Studio M2 Ultra 128GB	128 GB	UD-IQ4_XS	8.3	Too big
Mac Studio M1 Ultra 128GB	128 GB	UD-IQ4_XS	7.9	Too big
MacBook Pro M4 Max 128GB	128 GB	UD-IQ4_XS	6.2	Too big
MacBook Pro M4 Max 64GB	64 GB	UD-IQ4_XS	5.6	Too big
RTX 5090 32GB	32 GB	UD-IQ4_XS	4.2	Too big
2× RX 7900 XTX 24GB	48 GB	UD-IQ4_XS	4.1	Too big
MacBook Pro M3 Max 64GB	64 GB	UD-IQ4_XS	3.9	Too big
MacBook Pro M1 Max 64GB	64 GB	UD-IQ4_XS	3.6	Too big
MacBook Pro M4 Pro 48GB	48 GB	UD-IQ4_XS	3.4	Too big
2× RTX 4090 24GB	48 GB	UD-IQ4_XS	2.8	Too big
RTX 4090 24GB	24 GB	UD-IQ4_XS	2.7	Too big
RX 7900 XTX 24GB	24 GB	UD-IQ4_XS	2.4	Too big
2× RTX 3090 24GB	48 GB	UD-IQ4_XS	2.4	Too big
RTX 3090 24GB	24 GB	UD-IQ4_XS	2.3	Too big
RTX 4080 Super 16GB	16 GB	UD-IQ4_XS	2.1	Too big
4× RTX 3060 12GB	48 GB	UD-IQ4_XS	2.1	Too big
RTX 4070 12GB	12 GB	UD-IQ4_XS	2.0	Too big
RTX 3060 12GB	12 GB	UD-IQ4_XS	2.0	Too big
RTX 4060 8GB	8 GB	UD-IQ4_XS	2.0	Too big

Estimates for single-stream decoding at UD-IQ4_XS; 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 MiniMax M2.7 (230B params) fits at each quantization level on NVIDIA H200 141GB (141.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_KBest for your GPU	2	89.7 GB	Low	A84
Q3_K_S	3	112.7 GB	Low	F0
NVFP4	4	128.8 GB	Medium	F0
Q4_K_M	4	140.3 GB	Medium	F0
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 NVIDIA H200 141GB can run

Model	Params	Grade	Decode	Capabilities
Qwen 3 235B A22B	235B	A	56.1 tok/s

Frequently asked questions

Can NVIDIA H200 141GB run MiniMax M2.7?

Yes, NVIDIA H200 141GB can run MiniMax M2.7 with a A grade (Very compromised (needs ~15.9 GB host RAM)). Expected decode speed: 65.2 tok/s.

How much VRAM does MiniMax M2.7 need?

MiniMax M2.7 (230B parameters) requires approximately 159.1 GB of memory with UD-IQ4_XS quantization.

What is the best quantization for MiniMax M2.7?

The recommended quantization for MiniMax M2.7 is UD-IQ4_XS, which balances quality and memory efficiency.

What speed will MiniMax M2.7 run at on NVIDIA H200 141GB?

On NVIDIA H200 141GB, MiniMax M2.7 achieves approximately 65.2 tokens per second decode speed with a time-to-first-token of 2967ms using UD-IQ4_XS quantization.

Can NVIDIA H200 141GB run MiniMax M2.7 for coding?

For coding workloads, MiniMax M2.7 on NVIDIA H200 141GB receives a A grade with 65.2 tok/s and 4K context.

What context window can MiniMax M2.7 use on NVIDIA H200 141GB?

On NVIDIA H200 141GB, MiniMax M2.7 can safely use up to 4K tokens of context. The model's official context limit is 205K, but available memory constrains the safe maximum.

What should I upgrade first if MiniMax M2.7 feels slow on NVIDIA H200 141GB?

Remove offload with more accelerator memory. Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.

See all results for NVIDIA H200 141GB See all hardware for MiniMax M2.7

Embed this result▼

Paste this snippet into any page to show a live fit card.

<iframe src="https://willitrunai.com/embed/minimax-m2-7-on-h200-141gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: