Can MiniMax M2.7 run on NVIDIA DGX Spark 128GB?

YES — With Q3_K_S

B64Good

Estimated from fit model

MiniMax M2.7 needs ~130.4 GB VRAM. NVIDIA DGX Spark 128GB has 108.8 GB. With Q3_K_S quantization, expect ~3 tok/s.

Runtime: llama.cppCapacity: OffloadBandwidth: LowStack: 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.

MiniMax M2.7 at UD-IQ4_XS needs 158.0 GB — too much for NVIDIA DGX Spark 128GB (108.8 GB). Runs at Q3_K_S (130.4 GB) with low quality. 2 quantization levels fit.

Capabilities:

Select quantization to explore

F16 (Maximum quality) — 489.2 GB, exceeds 108.8 GB available

489.2 GB required108.8 GB available

450% VRAM needed

380.4 GB over capacity — needs offload or smaller quantization

Fit status

Too heavy

Decode

2.0 tok/s

TTFT

96800 ms

Safe context

Memory

489.2 GB / 108.8 GB

Offload

80%

Memory breakdown

Weights471.5 GB

KV Cache3.8 GB

Runtime0.9 GB

Headroom13.1 GB

See how fast it feels

With memory offload — actual speed may be lower

See how fast it feelsMiniMax M2.7 on NVIDIA DGX Spark 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: 2.0 tok/s decode · 96.8s TTFT (warm) · 5 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 20% 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.

Shared-memory contention still exists

The OS, browser, and inference runtime all compete for the same physical memory pool, so real-world headroom is less forgiving than raw capacity suggests.

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 18.7 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	F	Too heavy	2.0 tok/s	52507 ms	4K
Coding	F	Too heavy	2.0 tok/s	96800 ms	4K
Agentic Coding	F	Too heavy	2.0 tok/s	140800 ms	4K
Reasoning	F	Too heavy	2.0 tok/s	114400 ms	4K
RAG	F	Too heavy	2.0 tok/s	176000 ms	4K

Quantization options

How MiniMax M2.7 (230B params) fits at each quantization level on NVIDIA DGX Spark 128GB (92.2 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	89.7 GB	Low	F0
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

Upgrade options

Hardware that runs MiniMax M2.7 well

NVIDIA B200 180GBBudget pick

180 GB VRAM (+52)8000 GB/s (+7727)

Makes the model fit on the accelerator instead of staying completely out of reach.155.6 tok/s decode

Makes the model fit on the accelerator instead of staying completely out of reach.

Removes host-memory offload, which is usually the single biggest latency and throughput win.

~$30,000 MSRP

NVIDIA H200 141GBBest value

141 GB VRAM (+13)4800 GB/s (+4527)

Makes the model fit on the accelerator instead of staying completely out of reach.65.2 tok/s decode

Makes the model fit on the accelerator instead of staying completely out of reach.

Raises estimated decode speed by about 3160%.

~$30,000 MSRP

NVIDIA H200 PCIe 141GBNVIDIA upgrade

141 GB VRAM (+13)4800 GB/s (+4527)

Makes the model fit on the accelerator instead of staying completely out of reach.55.8 tok/s decode

Makes the model fit on the accelerator instead of staying completely out of reach.

Raises estimated decode speed by about 2690%.

~$30,000 MSRP

Frequently asked questions

Can NVIDIA DGX Spark 128GB run MiniMax M2.7?

Yes, NVIDIA DGX Spark 128GB can run MiniMax M2.7 at Q3_K_S quantization (Very compromised (needs ~18.7 GB host RAM)). The recommended UD-IQ4_XS requires 158.0 GB which exceeds available memory, but at Q3_K_S it needs only 130.4 GB. Expected decode speed: 3.0 tok/s.

How much VRAM does MiniMax M2.7 need?

MiniMax M2.7 (230B parameters) requires approximately 158.0 GB at UD-IQ4_XS quantization. On NVIDIA DGX Spark 128GB, it fits at Q3_K_S using 130.4 GB.

What is the best quantization for MiniMax M2.7?

The recommended quantization is UD-IQ4_XS, but on NVIDIA DGX Spark 128GB the best fitting quantization is Q3_K_S, which uses 130.4 GB.

What speed will MiniMax M2.7 run at on NVIDIA DGX Spark 128GB?

On NVIDIA DGX Spark 128GB, MiniMax M2.7 achieves approximately 3.0 tokens per second decode speed with a time-to-first-token of 63999ms using Q3_K_S quantization.

Can NVIDIA DGX Spark 128GB run MiniMax M2.7 for coding?

For coding workloads, MiniMax M2.7 on NVIDIA DGX Spark 128GB receives a F grade with 2.0 tok/s and 4K context.

What context window can MiniMax M2.7 use on NVIDIA DGX Spark 128GB?

On NVIDIA DGX Spark 128GB, MiniMax M2.7 can safely use up to 4K tokens of context at Q3_K_S quantization. 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 DGX Spark 128GB?

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.

Is unified memory on NVIDIA DGX Spark 128GB as fast as VRAM for MiniMax M2.7?

Not always. NVIDIA DGX Spark 128GB can often fit larger models thanks to unified memory, but a discrete GPU with dedicated high-bandwidth VRAM may still decode faster once the model fits. For this combination, the important distinction is capacity versus sustained throughput.

See all results for NVIDIA DGX Spark 128GB 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-dgx-spark-128gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview:

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 20% 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.

Shared-memory contention still exists

The OS, browser, and inference runtime all compete for the same physical memory pool, so real-world headroom is less forgiving than raw capacity suggests.

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 18.7 GB of extra host RAM just for the offloaded portion, before OS and other tools.

Workload

Grade

Fit

Decode

TTFT

Context

Chat

Too heavy

2.0 tok/s

52507 ms

Coding

Too heavy

2.0 tok/s

96800 ms

Agentic Coding

Too heavy

2.0 tok/s

140800 ms

Reasoning

Too heavy

2.0 tok/s

114400 ms

RAG

Too heavy

2.0 tok/s

176000 ms

Quant

Bits

VRAM

Quality

Fit

Q2_K

89.7 GB

Low

Q3_K_S

112.7 GB

Low

NVFP4

128.8 GB

Medium

Q4_K_M

140.3 GB

Medium

Q5_K_M

165.6 GB

High

Q6_K

188.6 GB

High

Q8_0

246.1 GB

Very High

F16

471.5 GB

Maximum

Frequently asked questions

Can NVIDIA DGX Spark 128GB run MiniMax M2.7?

How much VRAM does MiniMax M2.7 need?

MiniMax M2.7 (230B parameters) requires approximately 158.0 GB at UD-IQ4_XS quantization. On NVIDIA DGX Spark 128GB, it fits at Q3_K_S using 130.4 GB.

What is the best quantization for MiniMax M2.7?

The recommended quantization is UD-IQ4_XS, but on NVIDIA DGX Spark 128GB the best fitting quantization is Q3_K_S, which uses 130.4 GB.

What speed will MiniMax M2.7 run at on NVIDIA DGX Spark 128GB?

On NVIDIA DGX Spark 128GB, MiniMax M2.7 achieves approximately 3.0 tokens per second decode speed with a time-to-first-token of 63999ms using Q3_K_S quantization.

Can NVIDIA DGX Spark 128GB run MiniMax M2.7 for coding?

For coding workloads, MiniMax M2.7 on NVIDIA DGX Spark 128GB receives a F grade with 2.0 tok/s and 4K context.

What context window can MiniMax M2.7 use on NVIDIA DGX Spark 128GB?

On NVIDIA DGX Spark 128GB, MiniMax M2.7 can safely use up to 4K tokens of context at Q3_K_S quantization. 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 DGX Spark 128GB?

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.

Is unified memory on NVIDIA DGX Spark 128GB as fast as VRAM for MiniMax M2.7?