OpenModelsHQ

MiniMax-M1-40k

MiniMaxLLMMoEApache-2.0China Desk

MiniMax-M1-40k is an open-weight language model from MiniMax with 456B parameters (mixture of experts). At 4-bit it needs about 304 GB of memory, so the smallest device in our directory that fits it is the Mac Studio M3 Ultra (512GB), which is discontinued.

Overview

Estimated memory at 4-bit
304GB

Includes room for an 8k context and runtime overhead. More context needs more memory.

Total parameters
456B
Mixture of experts, all weights counted
Context window
10000K
10,240,000 tokens
Cheapest API, blended / 1M
No hosted API
Weights only

Key information

Lab
MiniMax
Released
5 Jun 2025
Parameters
456B · MoE
Type
Language
Context
10,240,000 tokens
License
Apache-2.0
HF downloads, 30 days
30,454
View all

Will it run on your hardware?

How we estimate
Memory needed vs devices
MiniMax-M1-40k needs about 304 GB at 4-bit, 534.8 GB at 8-bit and 1006.4 GB at 16-bit. At 4-bit it fits none of the reference devices. Dashed lines are usable memory on each device; a model fits when its estimate stays within 90% of it. Log scale. 8k context.
Memory needed vs devices: data
Estimate or deviceMemory
Q4304 GB
Q8534.8 GB
BF161006.4 GB
RTX 5060 Ti 16 GB16 GB usable
RTX 5090 32 GB32 GB usable
DGX Spark 128 GB108.8 GB usable
Mac Studio M5 Ultra 256 GB192 GB usable

Single-device memory estimate. Pick a device to update the On your device column.

36 GB usable memory

FormatMemory neededOn your deviceExample hardware
4-bit (Q4)≈ 304 GBToo big 844%Mac Studio M3 Ultra (512GB)Discontinued512 GB memory
8-bit (Q8)≈ 534.8 GBToo big 1486%No single device in our directory has enough memory
16-bit (BF16)≈ 1006.4 GBToo big 2796%No single device in our directory has enough memory

Fits means the estimate stays within 90% of usable memory. Tight is above 90% and up to 100%. Too big is above 100%. These are memory checks, not speed or compatibility tests.

Mac allowances are 66% of total RAM up to 36 GB, and 75% above. AI boxes allow 85% because their memory is shared with the operating system.

Where to run it

On a Mac

No trusted MLX build found yet.

Check your Mac

With GGUF

No trusted GGUF build found yet.

Find compatible hardware

Through an API

No hosted API found.

More about this model

Frequently asked questions

How much memory does MiniMax-M1-40k need? At an 8k context, about 304 GB at 4-bit, 534.8 GB at 8-bit and 1006.4 GB at 16-bit (BF16). A longer context needs more.

Can I run MiniMax-M1-40k on a Mac? No current Mac fits the 4-bit estimate of 304 GB. The smallest Mac in our directory that does is the Mac Studio M3 Ultra (512GB), which is discontinued. We have not found a trusted MLX or GGUF build yet.

Does the full context fit? MiniMax-M1-40k supports up to 10,240,000 tokens of context. Our memory estimates use 8k, so long prompts need more memory than shown.

What does it cost through an API? We did not find a hosted API for this model.

License in plain English

Apache-2.0. This license permits commercial use, modification and redistribution, with conditions such as keeping the required notices. This summary is not legal advice.

Read Apache-2.0

Read about this license

OMHQ RigBench

Not yet tested. We show no speed or quality score without a measurement.

Revision history and sources

Last updated . Sources:Hugging Face model card.