minimax M2.7
minimax M2-series model for coding, agentic workflows, and professional productivity. Among the most-pulled models in the Ollama library in 2026.
What minimax M2.7 is for
minimax M2.7 is a reasoning model: it spends output tokens working through a problem before answering, which makes it slower per useful word and better on problems that need the working shown. minimax released it in 2026-03 with a single 480B size under minimax License (open-weight), with a 128K context window. Budget for the extra tokens the thinking phase consumes. The catalogue records its strength as minimax M2-series for coding, agentic workflows, professional productivity (Mar 2026).
Sizes and memory
The 480B needs about 280 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 |
|---|---|---|---|
| 480B | 280 GB | 420 GB | None in this guide |
Hardware that runs minimax M2.7
No single card in our hardware guide holds minimax M2.7 at Q4_K_M: the smallest size on record is 280 GB of weights, and the largest capacity in the guide is 192 GB. Running it locally means several cards, or a machine with enough unified memory to treat the whole model as resident.
What people use it for
The catalogue lists 4 recorded uses for minimax M2.7: coding, agentic, professional productivity, chat. It is tagged chat, tools, coding, agentic, thinking.
Where minimax M2.7 sits in the minimax family
Our catalogue holds 5 minimax entries. Ordered by release date, minimax M2.7 (2026-03) is the 4th of them, and minimax M3 (2026-06) is newer.
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.
How to run minimax M2.7 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 M2.7 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 M2.7 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.