OpenModelsHQ

MiniMax-M3.1-Flash

MiniMaxVisionMoECustom licenseChina Desk

MiniMax-M3.1-Flash is an open-weight vision and language model from MiniMax with 220B parameters (mixture of experts). At 4-bit it needs about 146.6 GB of memory, so the smallest current device that fits it is the Mac Studio M5 Ultra (256GB).

Overview

Estimated memory at 4-bit
146.6GB

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

Total parameters
220B
Mixture of experts, all weights counted
Context window
1024K
1,048,576 tokens
Cheapest API, blended / 1M
$0.1312
₹12 · Inferact vLLM · 3:1 input to output
All MiniMax API prices

Key information

Lab
MiniMax
Released
17 Oct 2026
Parameters
220B · MoE
Type
Vision and language
Context
1,048,576 tokens
HF downloads, 30 days
61,559
View all

Will it run on your hardware?

How we estimate
Memory needed vs devices
MiniMax-M3.1-Flash needs about 146.6 GB at 4-bit, 258.2 GB at 8-bit and 486.2 GB at 16-bit. At 4-bit it fits Mac Studio M5 Ultra (256GB). 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
Q4146.6 GB
Q8258.2 GB
BF16486.2 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)≈ 146.6 GBToo big 407%Mac Studio M5 Ultra (256GB)256 GB memory
8-bit (Q8)≈ 258.2 GBToo big 717%RubinAnnounced288 GB memory
16-bit (BF16)≈ 486.2 GBToo big 1351%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

Choose a file for llama.cpp or a compatible app.

unsloth/MiniMax-M3.1-Flash-GGUFFind compatible hardware

Through an API

Inferact vLLM (nvfp4) is the cheapest provider we found.

$0.075 / $0.30

Input / output per 1M tokens
₹7.07 / ₹28 at ₹94.29 per $1

Blended: $0.1312 (₹12) per 1M. Ranked by a 3:1 mix of input and output tokens.

GGUF with llama.cppView repository
llama-cli -hf unsloth/MiniMax-M3.1-Flash-GGUF \
  -c 8192 -p "Explain how a transformer works."

Example commands built from the repository ids above. They need a working install of llama.cpp. We have not run them; check each repository for available files.

Hosted API 11

USD and INR per million tokensAll MiniMax API prices
Precision
Inferact vLLMCheapest$0.1312₹12$0.075₹7.07$0.30₹281,048,576NVFP4
StreamLake$0.2363₹22$0.135₹13$0.54₹511,000,000FP8
DigitalOcean$0.2625₹25$0.15₹14$0.60₹571,048,576Not listed
Fireworks$0.2625₹25$0.15₹14$0.60₹571,048,576Not listed
GMICloud$0.2625₹25$0.15₹14$0.60₹571,048,576FP8
InferenceNet$0.2625₹25$0.15₹14$0.60₹571,000,000FP4
Minimax$0.2625₹25$0.15₹14$0.60₹571,048,576Not listed
Nebius$0.2625₹25$0.15₹14$0.60₹571,048,576FP4
Parasail$0.2625₹25$0.15₹14$0.60₹571,048,576FP8
SambaNova$0.2625₹25$0.15₹14$0.60₹571,048,576Not listed
Together$0.2625₹25$0.15₹14$0.60₹571,048,576Not listed
View on OpenRouterEndpoint sourceSorted by the blended price: 3 parts input to 1 part output. Context limits differ by provider.

INR at ₹94.29 per $1. Prices fetched 14 Nov 2026.

More about this model

Frequently asked questions

How much memory does MiniMax-M3.1-Flash need? At an 8k context, about 146.6 GB at 4-bit, 258.2 GB at 8-bit and 486.2 GB at 16-bit (BF16). A longer context needs more.

Can I run MiniMax-M3.1-Flash on a Mac? The smallest current Mac that fits the 4-bit estimate of 146.6 GB is the Mac Studio M5 Ultra (256GB). We have not found a trusted MLX build yet, but a GGUF build is available.

Does the full context fit? MiniMax-M3.1-Flash supports up to 1,048,576 tokens of context. Our memory estimates use 8k, so long prompts need more memory than shown.

What does it cost through an API? The cheapest provider we found is Inferact vLLM, at $0.08 per 1M input tokens and $0.30 per 1M output tokens (₹7.07 and ₹28 at 94.29 rupees per dollar). Ranked by a 3:1 mix of input and output tokens.

License in plain English

Custom license. This model uses a custom license rather than a standard one. Read it on the model card before using the model commercially. This summary is not legal advice.

Read the license on the model card

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, GGUF repository, OpenRouter.