Hugging FaceA 426B, 26B active chat model from peasantsmith that reads pictures as well as text.
- Downloads
- 28K
- Likes
- 12
- Parameters
- 426B, 26B active
- Context
- 1M
- Licence
- other
Too big for this Mac
Its smallest size needs 168 GB of memory, more than M4 · 16 GB can give it.
MiniMax M3.1 Flash Maya 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.
Sizes
From peasantsmith/MiniMax-M3.1-Flash-Maya-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.
Run It Anywhere
MiniMax M3.1 Flash Maya is an open model, so any app that runs GGUF files can run it. These take the IQ1_S size from peasantsmith straight from Hugging Face.
- LM StudioMac, Windows, Linux
Open - JanMac, Windows, Linux
Open - MstyMac, Windows, Linux
Open - OllamaMac, Windows, Linux
ollama run hf.co/peasantsmith/MiniMax-M3.1-Flash-Maya-GGUF:IQ1_S - llama.cppMac, Windows, Linux
llama-server -hf peasantsmith/MiniMax-M3.1-Flash-Maya-GGUF:IQ1_S - Docker Model RunnerMac, Windows, Linux
docker model run hf.co/peasantsmith/MiniMax-M3.1-Flash-Maya-GGUF:IQ1_S
On every Mac
| Mac | Size | Fit | Memory | Writes |
|---|---|---|---|---|
| M6 · 16 GB | IQ1_S | Too big | 168 GB | |
| M6 · 24 GB | IQ1_S | Too big | 168 GB | |
| M6 · 32 GB | IQ1_S | Too big | 168 GB | |
| M5 · 16 GB | IQ1_S | Too big | 168 GB | |
| M5 · 24 GB | IQ1_S | Too big | 168 GB | |
| M5 · 32 GB | IQ1_S | Too big | 168 GB | |
| M5 Pro · 24 GB | IQ1_S | Too big | 168 GB | |
| M5 Pro · 48 GB | IQ1_S | Too big | 168 GB | |
| M5 Pro · 64 GB | IQ1_S | Too big | 168 GB | |
| M5 Max · 36 GB | IQ1_S | Too big | 168 GB | |
| M5 Max · 48 GB | IQ1_S | Too big | 168 GB | |
| M5 Max · 64 GB | IQ1_S | Too big | 168 GB | |
| M5 Max · 128 GB | IQ1_S | Runs well | 98 GB | 23 |
| M5 Ultra · 96 GB | IQ1_S | Too big | 168 GB | |
| M5 Ultra · 256 GB | IQ2_XXS | Runs great | 160 GB | 35 |
| M5 Ultra · 512 GB | IQ2_XXS | Runs great | 197 GB | 35 |
| M4 · 16 GB | IQ1_S | Too big | 168 GB | |
| M4 · 24 GB | IQ1_S | Too big | 168 GB | |
| M4 · 32 GB | IQ1_S | Too big | 168 GB | |
| M4 Pro · 24 GB | IQ1_S | Too big | 168 GB | |
| M4 Pro · 48 GB | IQ1_S | Too big | 168 GB | |
| M4 Pro · 64 GB | IQ1_S | Too big | 168 GB | |
| M4 Max · 36 GB | IQ1_S | Too big | 168 GB | |
| M4 Max · 48 GB | IQ1_S | Too big | 168 GB | |
| M4 Max · 64 GB | IQ1_S | Too big | 168 GB | |
| M4 Max · 96 GB | IQ1_S | Too big | 168 GB | |
| M4 Max · 128 GB | IQ1_S | Runs well | 98 GB | 16 |
| M3 · 8 GB | IQ1_S | Too big | 168 GB | |
| M3 · 16 GB | IQ1_S | Too big | 168 GB | |
| M3 · 24 GB | IQ1_S | Too big | 168 GB | |
| M3 Pro · 18 GB | IQ1_S | Too big | 168 GB | |
| M3 Pro · 36 GB | IQ1_S | Too big | 168 GB | |
| M3 Max · 36 GB | IQ1_S | Too big | 168 GB | |
| M3 Max · 48 GB | IQ1_S | Too big | 168 GB | |
| M3 Max · 64 GB | IQ1_S | Too big | 168 GB | |
| M3 Max · 96 GB | IQ1_S | Too big | 168 GB | |
| M3 Max · 128 GB | IQ1_S | Runs well | 98 GB | 13 |
| M3 Ultra · 96 GB | IQ1_S | Too big | 168 GB | |
| M3 Ultra · 256 GB | IQ2_XXS | Runs great | 160 GB | 19 |
| M3 Ultra · 512 GB | IQ2_XXS | Runs great | 197 GB | 19 |
| M2 · 8 GB | IQ1_S | Too big | 168 GB | |
| M2 · 16 GB | IQ1_S | Too big | 168 GB | |
| M2 · 24 GB | IQ1_S | Too big | 168 GB | |
| M2 Pro · 16 GB | IQ1_S | Too big | 168 GB | |
| M2 Pro · 32 GB | IQ1_S | Too big | 168 GB | |
| M2 Max · 32 GB | IQ1_S | Too big | 168 GB | |
| M2 Max · 64 GB | IQ1_S | Too big | 168 GB | |
| M2 Max · 96 GB | IQ1_S | Too big | 168 GB | |
| M2 Ultra · 64 GB | IQ1_S | Too big | 168 GB | |
| M2 Ultra · 128 GB | IQ1_S | Runs well | 98 GB | 22 |
| M2 Ultra · 192 GB | IQ2_XXS | Runs great | 127 GB | 19 |
| M1 · 8 GB | IQ1_S | Too big | 168 GB | |
| M1 · 16 GB | IQ1_S | Too big | 168 GB | |
| M1 Pro · 16 GB | IQ1_S | Too big | 168 GB | |
| M1 Pro · 32 GB | IQ1_S | Too big | 168 GB | |
| M1 Max · 32 GB | IQ1_S | Too big | 168 GB | |
| M1 Max · 64 GB | IQ1_S | Too big | 168 GB | |
| M1 Ultra · 64 GB | IQ1_S | Too big | 168 GB | |
| M1 Ultra · 128 GB | IQ1_S | Runs well | 98 GB | 17 |
Writes is words a second, estimated from the Mac's memory speed and the model's size; how, and how wrong.
Information
- Maker
- peasantsmith
- Released
- October 2026
- Parameters
- 426B, 26B active
- Longest chat
- 1M tokens
- Reads pictures
- Yes
- Licence
- other
- Downloads this month
- 27,920
- Likes
- 12
- Sizes
- 2, 93 to 122 GB
- Kind
- Maker's release
Badge for the model card
Shows on MiniMax M3.1 Flash Maya'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.