MiMo-V2.6-Pro
Grok 4.7
- Context
- 205Ktokens
- Released
- 10mo ago
- Size
- 229Bparameters
Earlier MiniMax agent model for practical coding and productivity tasks
- Language model
- Open weights · 229B
- Reasoning
- Tools
How it compares
Level
FlagshipThe lab's most capable generally available line, priced for hard tasks.
Flagship models from other labs
Vs. your stack
Add the models you use to see how this one compares.
Sign inAdditional source evidence
- Source model
- minimax/MiniMax-M2.1
- Source family
- minimax
- Last updated
- 2025-12-23
- Model context
- 205K
- Model output limit
- 131K
- Open weights
- Yes
- File attachments
- No
- Reasoning
- Yes
- Tool calling
- Yes
- Temperature control
- Yes
Downloadable weights
Published benchmarks
Complete source record (JSON)
{
"id": "minimax/MiniMax-M2.1",
"name": "MiniMax-M2.1",
"description": "Earlier MiniMax agent model for practical coding and productivity tasks",
"family": "minimax",
"last_updated": "2025-12-23",
"attachment": false,
"reasoning": true,
"tool_call": true,
"temperature": true,
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 204800,
"output": 131072
},
"benchmarks": [
{
"name": "SWE-Bench Verified",
"score": 74,
"source": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1",
"metric": "resolved"
},
{
"name": "SWE-Bench Pro",
"score": 36.81,
"source": "https://labs.scale.com/leaderboard/swe_bench_pro_public",
"metric": "resolve rate",
"dataset": "public"
}
],
"release_date": "2025-12-23",
"open_weights": true,
"weights": [
{
"label": "Hugging Face",
"url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1"
}
]
}Frequently asked questions
Running locally
MiniMax-M2.1 needs an estimated 159.9 GB of VRAM at Q4, 279.9 GB at Q8 and 526.5 GB at FP16. These figures are estimates from the 229B parameter count, covering weights plus about 15% and 0.5 GB for a short context.
No. On a 24 GB, 16 GB, 12 GB or 8 GB GPU, MiniMax-M2.1 does not fit at Q4, Q8 or FP16 (estimate).
Yes, at Q4. Assuming macOS lets the GPU use about 75% of unified memory, the smallest common Mac memory size that fits Q4 is an estimated 256 GB.
Privacy and data
Yes. MiniMax-M2.1 has open weights, so you can self-host it for full control of your data.
Capabilities and specs
The context window of MiniMax-M2.1 is 205K tokens (204,800) and the maximum output is 131K tokens (131,072).
No. MiniMax-M2.1 accepts text input only, so it cannot read images, audio, video or PDFs.
Yes, MiniMax-M2.1 supports tool calling (function calling).
Yes, MiniMax-M2.1 supports a reasoning mode.
Quality and benchmarks
Yes. MiniMax-M2.1 is ahead of its predecessor MiniMax-M2 on Terminal Bench, with no benchmarks where it is behind or level.
The closest alternatives to MiniMax-M2.1 are Bolmo 7B by Ai2, Olmo 3.1 32B Instruct by Ai2 and MiMo-V2-Flash by Xiaomi, matched on model kind and release date (no comparable price).
Bolmo 7BMiniMax-M2.1 vs Bolmo 7BOlmo 3.1 32B InstructMiniMax-M2.1 vs Olmo 3.1 32B InstructMiMo-V2-FlashMiniMax-M2.1 vs MiMo-V2-Flash
Licensing and access
MiniMax-M2.1 is open weights.
Download the MiniMax-M2.1 weights from the Hugging Face repository MiniMaxAI/MiniMax-M2.1.
Basics
MiniMax made MiniMax-M2.1, and it was released December 23, 2025.
Yes. MiniMax-M2.1 has open weights.
Generated from Vertical Tabs data, updated November 9, 2026.
Discussion
No comments yet
Be the first to share your thoughts.