Skip to content

MiniMax M3

MoEVision

MiniMaxMiniMax · 427B (23B active) · Mixture of experts

MiniMax M3 is a 427B model from MiniMax with a 1M-token context. At Q4_K_M with an 8K context it needs about 244.6 GB; 307 GB leaves room for longer chats.

Hugging Face GGUF

Mixture of experts

Parameters: 427B · Active: 23B

All 427B parameters load into memory, but only 23B work on each token, so it runs at the speed of a much smaller model.

Quantization options

QuantMemoryOn your hardware
Q2_K—…
Q3_K_M—…
Q4_K_M—…
Q5_K_M—…
Q6_K—…
Q8_0—…
F16—…

Memory by context length

At Q4_K_M. The context cache grows with every token the model keeps in mind.

ContextContext cacheTotal
4K0.5 GB244.1 GB
8K0.9 GB244.6 GB
32K3.8 GB247.4 GB
128K15 GB258.6 GB
256K30 GB273.6 GB

Share a measured speed

Run one of these and paste the whole output below (or just the tokens per second):

llama-bench -m model.gguf
ollama run model --verbose

Published anonymously and kept. We store no account or address, only a daily-changing hash for a limit of ten submissions a day.

Next steps

Least hardware that runs it well

Desktop devices with the least memory that give MiniMax M3 grade A or S at Q4_K_M.

Can I run MiniMax M3 locally?

Can I run MiniMax M3 locally?

Yes, if your GPU or Mac has about 244.6 GB free for it at Q4_K_M. Open this page on that computer to see the grade for your exact hardware, then start it with llama.cpp, Ollama or LM Studio.

How much memory does MiniMax M3 need?

About 244.6 GB at Q4_K_M with an 8K context and 422.9 GB at Q8_0. Lower quantizations fit smaller cards with some loss in quality; longer contexts add to the total.