Hugging FaceA 229B, 11B active chat model from MiniMax.
- Rating
- 3.5
- Downloads
- 8.1K
- Likes
- 199
- Parameters
- 229B, 11B active
- Context
- 192K
- Licence
- other
Too big for this Mac
Its smallest size needs 65 GB of memory, more than M4 · 16 GB can give it.
Ratings
3.5 out of 5, across the tests below.
MMLU-Pro: graduate-level questions in 14 subjects. GPQA Diamond: questions PhD scientists write for each other. Humanity's Last Exam: questions written to be beyond today's models. SWE-bench Verified: real GitHub issues fixed so the project's tests pass. Terminal-Bench 2.0: jobs finished alone in a terminal. Scores are the ones filed on the model's Hugging Face page or the board's own table, read 2026-11-05; some come from the maker.
MiniMax M2.1 runs well from a Mac with an M2 Max and 96 GB of memory. 15 of 59 Mac configurations run it well.
Compare with
The nearest models in size.
- MiniMax M2.7MiniMax · 15K downloads · Arena 1415Too big for this Mac · 47 GB
- MiniMax M2MiniMax · 8.8K downloads · Arena 1344Too big for this Mac · 56 GB
- MiniMax M2.5MiniMax · 4.3K downloads · Arena 1391Too big for this Mac · 56 GB
- Qwen3 235B A22B 2507Alibaba Qwen · 24K downloadsToo big for this Mac · 53 GB
Sizes
From unsloth/MiniMax-M2.1-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.
| Size | Download | Memory at 8K | Get |
|---|---|---|---|
| UD-TQ1_0 | 56 GB | 57 GBestimated | Open |
| UD-IQ1_S | 63 GB | 64 GBestimated | Open |
| UD-IQ1_M | 68 GB | 70 GBestimated | Open |
| UD-IQ2_XXS | 74 GB | 75 GBestimated | Open |
| UD-IQ2_M | 78 GB | 79 GBestimated | Open |
| Q2_K | 83 GB | 85 GBestimated | Open |
| Q2_K_L | 83 GB | 85 GBestimated | Open |
| UD-Q2_K_XL | 86 GB | 87 GBestimated | Open |
| UD-IQ3_XXS | 93 GB | 95 GBestimated | Open |
| Q3_K_S | 99 GB | 100 GBestimated | Open |
| UD-Q3_K_XL | 101 GB | 103 GBestimated | Open |
| Q3_K_M | 109 GB | 111 GBestimated | Open |
| IQ4_XS | 122 GB | 123 GBestimated | Open |
| IQ4_NL | 129 GB | 130 GBestimated | Open |
| Q4_0 | 130 GB | 131 GBestimated | Open |
| Q4_K_S | 130 GB | 131 GBestimated | Open |
| UD-Q4_K_XL | 131 GB | 133 GBestimated | Open |
| Q4_K_M | 138 GB | 140 GBestimated | Open |
| Q4_1 | 143 GB | 144 GBestimated | Open |
| Q5_K_S | 157 GB | 159 GBestimated | Open |
| UD-Q5_K_XL | 162 GB | 163 GBestimated | Open |
| Q5_K_M | 162 GB | 164 GBestimated | Open |
| Q6_K | 188 GB | 189 GBestimated | Open |
| UD-Q6_K_XL | 194 GB | 196 GBestimated | Open |
| Q8_0 | 243 GB | 244 GBestimated | Open |
| UD-Q8_K_XL | 261 GB | 263 GBestimated | Open |
| BF16 | 457 GB | 459 GBestimated | Open |
Run It Anywhere
MiniMax M2.1 is an open model, so any app that runs GGUF files can run it. These take the UD-TQ1_0 size from unsloth straight from Hugging Face.
- LM StudioMac, Windows, Linux
Open - JanMac, Windows, Linux
Open - MstyMac, Windows, Linux
Open - OllamaMac, Windows, Linux
ollama run hf.co/unsloth/MiniMax-M2.1-GGUF:UD-TQ1_0 - llama.cppMac, Windows, Linux
llama-server -hf unsloth/MiniMax-M2.1-GGUF:UD-TQ1_0 - Docker Model RunnerMac, Windows, Linux
docker model run hf.co/unsloth/MiniMax-M2.1-GGUF:UD-TQ1_0
On a PC Graphics Card
| Video memory | Largest size that fits | Download | Memory at 8K |
|---|---|---|---|
| 6 GB | None worth running | needs 79 GB | |
| 8 GB | None worth running | needs 79 GB | |
| 10 GB | None worth running | needs 79 GB | |
| 11 GB | None worth running | needs 79 GB | |
| 12 GB | None worth running | needs 79 GB | |
| 16 GB | None worth running | needs 79 GB | |
| 20 GB | None worth running | needs 79 GB | |
| 24 GB | None worth running | needs 79 GB | |
| 32 GB | None worth running | needs 79 GB | |
| 48 GB | None worth running | needs 79 GB |
The largest size, of those that keep three bits a weight or more, whose memory at an 8K chat is under 92% of the card's; the rest is the desktop's. Estimated from the files, the same way as for a Mac; speed on a PC is not estimated yet. A size that doesn't fit the card still runs, slower, with part of it in ordinary memory.
On every Mac
| Mac | Size | Fit | Memory | Writes |
|---|---|---|---|---|
| M6 · 16 GB | IQ1_S | Too big | 65 GB | |
| M6 · 24 GB | IQ1_S | Too big | 65 GB | |
| M6 · 32 GB | IQ1_S | Too big | 65 GB | |
| M5 · 16 GB | IQ1_S | Too big | 65 GB | |
| M5 · 24 GB | IQ1_S | Too big | 65 GB | |
| M5 · 32 GB | IQ1_S | Too big | 65 GB | |
| M5 Pro · 24 GB | IQ1_S | Too big | 65 GB | |
| M5 Pro · 48 GB | IQ1_S | Too big | 65 GB | |
| M5 Pro · 64 GB | IQ1_S | Tight fit | 49 GB | 12 |
| M5 Max · 36 GB | IQ1_S | Too big | 65 GB | |
| M5 Max · 48 GB | IQ1_S | Too big | 65 GB | |
| M5 Max · 64 GB | IQ1_S | Tight fit | 49 GB | 22 |
| M5 Max · 128 GB | Q3_K_S | Runs well | 100 GB | 18 |
| M5 Ultra · 96 GB | UD-IQ1_S | Runs well | 68 GB | 38 |
| M5 Ultra · 256 GB | Q5_K_M | Runs great | 171 GB | 27 |
| M5 Ultra · 512 GB | Q8_0 | Runs great | 261 GB | 26 |
| M4 · 16 GB | IQ1_S | Too big | 65 GB | |
| M4 · 24 GB | IQ1_S | Too big | 65 GB | |
| M4 · 32 GB | IQ1_S | Too big | 65 GB | |
| M4 Pro · 24 GB | IQ1_S | Too big | 65 GB | |
| M4 Pro · 48 GB | IQ1_S | Too big | 65 GB | |
| M4 Pro · 64 GB | IQ1_S | Tight fit | 49 GB | 9.3 |
| M4 Max · 36 GB | IQ1_S | Too big | 65 GB | |
| M4 Max · 48 GB | IQ1_S | Too big | 65 GB | |
| M4 Max · 64 GB | IQ1_S | Tight fit | 49 GB | 15 |
| M4 Max · 96 GB | UD-IQ1_S | Runs well | 68 GB | 12 |
| M4 Max · 128 GB | Q3_K_S | Runs well | 100 GB | 13 |
| M3 · 8 GB | IQ1_S | Too big | 65 GB | |
| M3 · 16 GB | IQ1_S | Too big | 65 GB | |
| M3 · 24 GB | IQ1_S | Too big | 65 GB | |
| M3 Pro · 18 GB | IQ1_S | Too big | 65 GB | |
| M3 Pro · 36 GB | IQ1_S | Too big | 65 GB | |
| M3 Max · 36 GB | IQ1_S | Too big | 65 GB | |
| M3 Max · 48 GB | IQ1_S | Too big | 65 GB | |
| M3 Max · 64 GB | IQ1_S | Tight fit | 49 GB | 13 |
| M3 Max · 96 GB | UD-IQ1_S | Runs well | 68 GB | 9.7 |
| M3 Max · 128 GB | Q3_K_S | Runs well | 100 GB | 11 |
| M3 Ultra · 96 GB | UD-IQ1_S | Runs well | 68 GB | 20 |
| M3 Ultra · 256 GB | Q5_K_M | Runs great | 171 GB | 16 |
| M3 Ultra · 512 GB | Q8_0 | Runs great | 261 GB | 15 |
| M2 · 8 GB | IQ1_S | Too big | 65 GB | |
| M2 · 16 GB | IQ1_S | Too big | 65 GB | |
| M2 · 24 GB | IQ1_S | Too big | 65 GB | |
| M2 Pro · 16 GB | IQ1_S | Too big | 65 GB | |
| M2 Pro · 32 GB | IQ1_S | Too big | 65 GB | |
| M2 Max · 32 GB | IQ1_S | Too big | 65 GB | |
| M2 Max · 64 GB | IQ1_S | Tight fit | 49 GB | 13 |
| M2 Max · 96 GB | UD-IQ1_S | Runs well | 68 GB | 12 |
| M2 Ultra · 64 GB | IQ1_S | Tight fit | 49 GB | 21 |
| M2 Ultra · 128 GB | Q3_K_S | Runs well | 100 GB | 18 |
| M2 Ultra · 192 GB | Q4_K_S | Runs great | 131 GB | 17 |
| M1 · 8 GB | IQ1_S | Too big | 65 GB | |
| M1 · 16 GB | IQ1_S | Too big | 65 GB | |
| M1 Pro · 16 GB | IQ1_S | Too big | 65 GB | |
| M1 Pro · 32 GB | IQ1_S | Too big | 65 GB | |
| M1 Max · 32 GB | IQ1_S | Too big | 65 GB | |
| M1 Max · 64 GB | IQ1_S | Tight fit | 49 GB | 11 |
| M1 Ultra · 64 GB | IQ1_S | Tight fit | 49 GB | 17 |
| M1 Ultra · 128 GB | Q3_K_S | Runs well | 100 GB | 15 |
Writes is words a second, estimated from the Mac's memory speed and the model's size; how, and how wrong.
Packaged by
2 repositories on Hugging Face carry this model for llama.cpp. Outmake reads them all as one model.
Information
- Maker
- MiniMax
- Released
- December 2025
- Parameters
- 229B, 11B active
- Longest chat
- 192K tokens
- Reads pictures
- No
- Licence
- other
- Downloads this month
- 8,067
- Likes
- 199
- Sizes
- 27, 56 to 457 GB
- Kind
- Maker's release
- Source
- MiniMaxAI/MiniMax-M2.1
Badge for the model card
Shows on MiniMax M2.1's Hugging Face card which Macs run it well, linked to this page. It updates every morning.
Files, downloads and likes read from Hugging Face on November 5, 2026 and refreshed every morning. Memory and speed are estimates until someone running Outmake measures this model on that Mac.