minimax M2.1

What minimax M2.1 is for

minimax M2.1 is a general-purpose open-weights model from minimax, released in 2025-12 with a single 230B size and 128K of context, licensed minimax License (open-weight). The catalogue records its strength as December 2025 update to minimax M2.

Sizes and memory

The 230B needs about 130 GB of weights at Q4_K_M. That is the whole range; there is no larger or smaller variant in this record. Recommended VRAM adds roughly half again on top of the weights for the KV cache and the runtime.

Size	Weights at Q4_K_M	Recommended VRAM	Smallest card in our guide that holds it
230B	130 GB	195 GB	Apple M3 Ultra

Hardware that runs minimax M2.1

2 of the 19 cards in our hardware guide hold at least one size of minimax M2.1 at Q4_K_M. The cheapest that does is the Apple M3 Ultra at about $4000, running the 230B.

The largest size any of them holds is the 230B at 130 GB, on the Apple M3 Ultra (192 GB at 800 GB/s). Bandwidth, not capacity, sets the speed once a size fits, so a card further down the list with faster memory will generate more tokens per second on the same weights than a larger, slower one.

What people use it for

The catalogue lists 3 recorded uses for minimax M2.1: multilingual, code, agentic. It is tagged chat, tools, multilingual.

Where minimax M2.1 sits in the minimax family

Our catalogue holds 5 minimax entries. Ordered by release date, minimax M2.1 (2025-12) is the 2nd of them, and minimax M3 (2026-06) is newer. minimax M2 and minimax M2.5 and minimax M3 carry the same recorded memory footprint, so choosing between those and this one is a question of behaviour rather than of hardware: minimax M2.1 is the one recorded here for December 2025 update to minimax M2.

It ships under the minimax License (open-weight), which is neither a standard open-source licence nor a closed one. Read the terms before shipping anything commercial on top of it.

Context window: 128K

128K tokens is roughly 96,000 words at the usual ratio, which is a small repository or a whole book. Two cautions come with a window this size: the KV cache at full length can rival the weights for memory, and models rarely use the far end of their advertised context as well as they use the near end. Treat it as headroom, not as a promise.

Read the minimax M3 page instead

Our catalogue records the same publisher, the same size, the same 96 GB memory floor and the same 128K context window for minimax M2, minimax M2.1, minimax M2.5, minimax M3. Where we cannot show you how two releases differ in anything a reader would act on, publishing both as competing search results would be a guess dressed as a recommendation.

So minimax M3 (2026-06), the most recent of the 4, is the one we put in front of that question, and this page is marked noindex. It stays published because the record is real and someone running minimax M2.1 today should still be able to look it up. When a figure appears that separates them, this page returns to the index on its own.

How to run minimax M2.1 locally

Our catalogue does not record registry tags, so look the current tag up in the Ollama library or on Hugging Face before pasting these. The commands below are the shape of the workflow, not a copy-and-paste recipe.

Option 1: Ollama (simplest)

# find the tag for minimax M2.1 at ollama.com/library
ollama run <tag>

Option 2: Mullama (production)

mullama pull <tag>
mullama run <tag>

Option 3: llama.cpp (CLI)

# download a GGUF from Hugging Face, searching for "minimax M2.1 GGUF"
./llama-cli -m model.Q4_K_M.gguf -p "Hello, AI!"

Option 4: Python with Mullama or llama-cpp-python

from mullama import Model, Context
model = Model.load("model.Q4_K_M.gguf", n_gpu_layers=99)
ctx = Context(model, n_ctx=4096)
print(ctx.generate("Hello, AI!", 256))

Sources

Model record from src/data/models.json (2026-06-29); card capacities from src/data/gpus.json (2026-06-29). Upstream: Curated from ollama.com/library + community benchmarks + paperswithcode + huggingface.