Can MiniMax M2.7 run on B100 192GB?

YES — Tight Fit

S90Excellent

Estimated from fit model

MiniMax M2.7 needs ~164.2 GB VRAM. B100 192GB has 192.0 GB. With UD-IQ4_XS quantization, expect ~156 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) — 495.4 GB, exceeds 192.0 GB available

495.4 GB required192.0 GB available

258% VRAM needed

303.4 GB over capacity — needs offload or smaller quantization

Fit status

Too heavy

Decode

11.6 tok/s

TTFT

16731 ms

Safe context

Memory

495.4 GB / 192.0 GB

Offload

60%

Memory breakdown

Weights471.5 GB

KV Cache3.8 GB

Runtime0.9 GB

Headroom19.2 GB

See how fast it feels

With memory offload — actual speed may be lower

See how fast it feelsMiniMax M2.7 on B100 192GB
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: 11.6 tok/s decode · 16.7s TTFT (warm) · 29 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	155.6 tok/s	679 ms	134K
Coding	S	Tight fit	155.6 tok/s	1244 ms	134K
Agentic Coding	S	Tight fit	155.6 tok/s	1810 ms	134K
Reasoning	S	Tight fit	155.6 tok/s	1471 ms	134K
RAG	S	Tight fit	155.6 tok/s	2262 ms	134K

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 B100 192GB (192.0 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 B100 192GB can run

Model	Params	Grade	Decode	Capabilities
DeepSeek V4 Flash	284B	S	144.8 tok/s
Qwen 3 235B A22B	235B	S	136.8 tok/s

Frequently asked questions

Can B100 192GB run MiniMax M2.7?

Yes, B100 192GB can run MiniMax M2.7 with a S grade (Tight fit). Expected decode speed: 155.6 tok/s.

How much VRAM does MiniMax M2.7 need?

MiniMax M2.7 (230B parameters) requires approximately 164.2 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 B100 192GB?

On B100 192GB, MiniMax M2.7 achieves approximately 155.6 tokens per second decode speed with a time-to-first-token of 1244ms using UD-IQ4_XS quantization.

Can B100 192GB run MiniMax M2.7 for coding?

For coding workloads, MiniMax M2.7 on B100 192GB receives a S grade with 155.6 tok/s and 134K context.

What context window can MiniMax M2.7 use on B100 192GB?

On B100 192GB, MiniMax M2.7 can safely use up to 134K tokens of context. The model's official context limit is 205K, but available memory constrains the safe maximum.

See all results for B100 192GB 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-b100-192gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview:

Workload

Grade

Fit

Decode

TTFT

Context

Chat

Tight fit

155.6 tok/s

679 ms

134K

Coding

Tight fit

155.6 tok/s

1244 ms

134K

Agentic Coding

Tight fit

155.6 tok/s

1810 ms

134K

Reasoning

Tight fit

155.6 tok/s

1471 ms

134K

RAG

Tight fit

155.6 tok/s

2262 ms

134K

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

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

Quantization options

How MiniMax M2.7 (230B params) fits at each quantization level on B100 192GB (192.0 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

Model

Params

Grade

Decode

Capabilities

DeepSeek V4 Flash

284B

144.8 tok/s

Qwen 3 235B A22B

235B

136.8 tok/s

Frequently asked questions

Can B100 192GB run MiniMax M2.7?

Yes, B100 192GB can run MiniMax M2.7 with a S grade (Tight fit). Expected decode speed: 155.6 tok/s.

How much VRAM does MiniMax M2.7 need?

MiniMax M2.7 (230B parameters) requires approximately 164.2 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 B100 192GB?

On B100 192GB, MiniMax M2.7 achieves approximately 155.6 tokens per second decode speed with a time-to-first-token of 1244ms using UD-IQ4_XS quantization.

Can B100 192GB run MiniMax M2.7 for coding?

For coding workloads, MiniMax M2.7 on B100 192GB receives a S grade with 155.6 tok/s and 134K context.

What context window can MiniMax M2.7 use on B100 192GB?

On B100 192GB, MiniMax M2.7 can safely use up to 134K tokens of context. The model's official context limit is 205K, but available memory constrains the safe maximum.