Hugging FaceA 426B, 26B active chat model from MiniMax that reads pictures as well as text.
- Downloads
- 42K
- Likes
- 62
- Parameters
- 426B, 26B active
- Context
- 1M
- Licence
- other
Too big for this Mac
Its smallest size needs 169 GB of memory, more than M4 · 16 GB can give it.
Ratings
Humanity's Last Exam: questions written to be beyond today's models. 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 M3.1 Flash runs well from a Mac with an M1 Ultra and 128 GB of memory. 10 of 59 Mac configurations run it well.
Compare with
The nearest models in size.
- MiniMax M3.1 Flash Mayapeasantsmith · 28K downloadsToo big for this Mac · 93 GB
- MiniMax M3MiniMax · 14K downloads · Arena 1439Too big for this Mac · 91 GB
- Ornith 1.5 397Bornith-ai · 1.3M downloadsToo big for this Mac · 82 GB
- Qwen3.5 397BAlibaba Qwen · 36K downloads · Arena 1441Too big for this Mac · 89 GB
Sizes
From unsloth/MiniMax-M3.1-Flash-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.
| Size | Download | Memory at 8K | Get |
|---|---|---|---|
| UD-IQ1_M | 129 GB | 130 GBestimated | Open |
| UD-IQ2_XXS | 135 GB | 136 GBestimated | Open |
| UD-Q2_K_XL | 144 GB | 145 GBestimated | Open |
| UD-IQ3_XXS | 160 GB | 161 GBestimated | Open |
| UD-IQ3_S | 175 GB | 176 GBestimated | Open |
| UD-Q3_K_XL | 194 GB | 195 GBestimated | Open |
| UD-Q4_K_XL | 249 GB | 250 GBestimated | Open |
Run It Anywhere
MiniMax M3.1 Flash is an open model, so any app that runs GGUF files can run it. These take the UD-IQ1_M 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-M3.1-Flash-GGUF:UD-IQ1_M - llama.cppMac, Windows, Linux
llama-server -hf unsloth/MiniMax-M3.1-Flash-GGUF:UD-IQ1_M - Docker Model RunnerMac, Windows, Linux
docker model run hf.co/unsloth/MiniMax-M3.1-Flash-GGUF:UD-IQ1_M
On a PC Graphics Card
| Video memory | Largest size that fits | Download | Memory at 8K |
|---|---|---|---|
| 6 GB | None worth running | needs 145 GB | |
| 8 GB | None worth running | needs 145 GB | |
| 10 GB | None worth running | needs 145 GB | |
| 11 GB | None worth running | needs 145 GB | |
| 12 GB | None worth running | needs 145 GB | |
| 16 GB | None worth running | needs 145 GB | |
| 20 GB | None worth running | needs 145 GB | |
| 24 GB | None worth running | needs 145 GB | |
| 32 GB | None worth running | needs 145 GB | |
| 48 GB | None worth running | needs 145 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 | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M6 · 24 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M6 · 32 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M5 · 16 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M5 · 24 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M5 · 32 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M5 Pro · 24 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M5 Pro · 48 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M5 Pro · 64 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M5 Max · 36 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M5 Max · 48 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M5 Max · 64 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M5 Max · 128 GB | IQ1_S | Runs well | 100 GB | 23 |
| M5 Ultra · 96 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M5 Ultra · 256 GB | UD-IQ3_XXS | Runs great | 169 GB | 30 |
| M5 Ultra · 512 GB | UD-Q4_K_XL | Runs great | 324 GB | 23 |
| M4 · 16 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M4 · 24 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M4 · 32 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M4 Pro · 24 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M4 Pro · 48 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M4 Pro · 64 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M4 Max · 36 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M4 Max · 48 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M4 Max · 64 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M4 Max · 96 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M4 Max · 128 GB | IQ1_S | Runs well | 100 GB | 16 |
| M3 · 8 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M3 · 16 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M3 · 24 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M3 Pro · 18 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M3 Pro · 36 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M3 Max · 36 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M3 Max · 48 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M3 Max · 64 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M3 Max · 96 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M3 Max · 128 GB | IQ1_S | Runs well | 100 GB | 13 |
| M3 Ultra · 96 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M3 Ultra · 256 GB | UD-IQ3_XXS | Runs great | 169 GB | 17 |
| M3 Ultra · 512 GB | UD-Q4_K_XL | Runs great | 324 GB | 13 |
| M2 · 8 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M2 · 16 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M2 · 24 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M2 Pro · 16 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M2 Pro · 32 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M2 Max · 32 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M2 Max · 64 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M2 Max · 96 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M2 Ultra · 64 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M2 Ultra · 128 GB | IQ1_S | Runs well | 100 GB | 21 |
| M2 Ultra · 192 GB | UD-IQ1_M | Runs great | 131 GB | 19 |
| M1 · 8 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M1 · 16 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M1 Pro · 16 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M1 Pro · 32 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M1 Max · 32 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M1 Max · 64 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M1 Ultra · 64 GB | MiniMax-M3.1-Flash-IQ1_S-gptq | Too big | 169 GB | |
| M1 Ultra · 128 GB | IQ1_S | Runs well | 100 GB | 17 |
Writes is words a second, estimated from the Mac's memory speed and the model's size; how, and how wrong.
Packaged by
3 repositories on Hugging Face carry this model for llama.cpp. Outmake reads them all as one model.
Information
- Maker
- MiniMax
- Released
- October 2026
- Parameters
- 426B, 26B active
- Longest chat
- 1M tokens
- Reads pictures
- Yes
- Licence
- other
- Downloads this month
- 42,433
- Likes
- 62
- Sizes
- 7, 129 to 249 GB
- Kind
- Maker's release
Badge for the model card
Shows on MiniMax M3.1 Flash'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.