Can MiniMax M2.7 run on Gaudi 3 128GB?

YES — With NVFP4

A78Great

Estimated from fit model

MiniMax M2.7 needs ~146.3 GB VRAM. Gaudi 3 128GB has 128.0 GB. With NVFP4 quantization, expect ~40 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.

MiniMax M2.7 at UD-IQ4_XS needs 157.8 GB — too much for Gaudi 3 128GB (128.0 GB). Runs at NVFP4 (146.3 GB) with medium quality. 3 quantization levels fit.

Capabilities:

Select quantization to explore

F16 (Maximum quality) — 489.0 GB, exceeds 128.0 GB available

489.0 GB required128.0 GB available

382% VRAM needed

361.0 GB over capacity — needs offload or smaller quantization

Fit status

Too heavy

Decode

3.7 tok/s

TTFT

51666 ms

Safe context

Memory

489.0 GB / 128.0 GB

Offload

70%

Memory breakdown

Weights471.5 GB

KV Cache3.8 GB

Runtime0.9 GB

Headroom12.8 GB

See how fast it feels

With memory offload — actual speed may be lower

See how fast it feelsMiniMax M2.7 on Gaudi 3 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: 3.7 tok/s decode · 51.7s TTFT (warm) · 9 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.

Runtime ecosystem is narrower than CUDA

Intel GPUs can look attractive on memory per dollar, but local AI tooling, kernels, and model coverage are still broader and easier on CUDA today.

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.

Prefer CUDA if you want the path of least resistance

If your goal is maximum runtime coverage, easier troubleshooting, and better support for new local AI releases, CUDA is usually still the safer upgrade path.

Buy headroom, not only minimum fit

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

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	F	Too heavy	30.7 tok/s	3443 ms	4K
Coding	F	Too heavy	29.9 tok/s	6469 ms	4K
Agentic Coding	F	Too heavy	28.5 tok/s	9876 ms	4K
Reasoning	F	Too heavy	29.9 tok/s	7645 ms	4K
RAG	F	Too heavy	28.5 tok/s	12345 ms	4K

Quantization options

How MiniMax M2.7 (230B params) fits at each quantization level on Gaudi 3 128GB (128.0 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

Upgrade-Optionen

Hardware, die MiniMax M2.7 gut ausführt

Mac Studio M3 Ultra 256GBGünstige Wahl

256 GB Unified (+128)

Makes the model fit on the accelerator instead of staying completely out of reach.20 tok/s Dekodierung

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.

ca. $6,999 MSRP

AMD Instinct MI350X 288GBBestes Preis-Leistungs-Verhältnis

288 GB VRAM (+160)8000 GB/s (+4300)

Makes the model fit on the accelerator instead of staying completely out of reach.135.2 tok/s Dekodierung

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.

ca. $8,000 MSRP

Frequently asked questions

Can Gaudi 3 128GB run MiniMax M2.7?

Yes, Gaudi 3 128GB can run MiniMax M2.7 at NVFP4 quantization (Very compromised (needs ~16.1 GB host RAM)). The recommended UD-IQ4_XS requires 157.8 GB which exceeds available memory, but at NVFP4 it needs only 146.3 GB. Expected decode speed: 39.9 tok/s.

How much VRAM does MiniMax M2.7 need?

MiniMax M2.7 (230B parameters) requires approximately 157.8 GB at UD-IQ4_XS quantization. On Gaudi 3 128GB, it fits at NVFP4 using 146.3 GB.

What is the best quantization for MiniMax M2.7?

The recommended quantization is UD-IQ4_XS, but on Gaudi 3 128GB the best fitting quantization is NVFP4, which uses 146.3 GB.

What speed will MiniMax M2.7 run at on Gaudi 3 128GB?

On Gaudi 3 128GB, MiniMax M2.7 achieves approximately 39.9 tokens per second decode speed with a time-to-first-token of 4847ms using NVFP4 quantization.

Can Gaudi 3 128GB run MiniMax M2.7 for coding?

For coding workloads, MiniMax M2.7 on Gaudi 3 128GB receives a F grade with 29.9 tok/s and 4K context.

What context window can MiniMax M2.7 use on Gaudi 3 128GB?

On Gaudi 3 128GB, MiniMax M2.7 can safely use up to 4K tokens of context at NVFP4 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 Gaudi 3 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.

Would CUDA be a better path than Gaudi 3 128GB for MiniMax M2.7?

Often yes, if your goal is the easiest setup and the widest runtime support. Intel can offer attractive memory capacity, but CUDA still tends to win on tooling maturity, guides, kernels, and model coverage for local AI.

See all results for Gaudi 3 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-gaudi-3-128gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: