A 310B, 6.2B active chat model from Xiaomi.
- Rating
- 4.5
- Downloads
- 3.6K
- Likes
- 51
- Parameters
- 310B, 6.2B active
- Context
- 1M
- Licence
- mit
Too big for this Mac
Its smallest size needs 107 GB of memory, more than M4 · 16 GB can give it.
Ratings
4.5 out of 5, across people's blind votes on its answers and the tests below.
LM Arena ratings of October 28, 2026 (CC BY 4.0): people vote between two answers without knowing which model wrote which. The bar ends at 1488, the best any open model has. The Arena tests the full model; a small size on a Mac answers a little worse.
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.
MiMo V2.5 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.
- MiMo V2.6 Flash RLXiaomi · 47K downloadsToo big for this Mac · 108 GB
- MiMo V2 FlashXiaomi · 21K downloads · Arena 1386Too big for this Mac · 78 GB
- Hy3Tencent · 147K downloads · Arena 1454Too big for this Mac · 64 GB
- Llama 3 1 Nemotron Ultra 253B V1NVIDIA · 2.2K downloads · Arena 1348Too big for this Mac · 54 GB
Sizes
From unsloth/MiMo-V2.5-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 | 93 GB | 93 GBestimated | Open |
| UD-IQ2_XXS | 96 GB | 97 GBestimated | Open |
| UD-IQ2_M | 97 GB | 97 GBestimated | Open |
| UD-Q2_K_XL | 103 GB | 103 GBestimated | Open |
| UD-IQ3_S | 115 GB | 115 GBestimated | Open |
| UD-IQ3_XXS | 126 GB | 126 GBestimated | Open |
| UD-Q3_K_M | 140 GB | 140 GBestimated | Open |
| UD-Q3_K_XL | 140 GB | 140 GBestimated | Open |
| UD-IQ4_XS | 149 GB | 150 GBestimated | Open |
| UD-IQ4_NL | 153 GB | 153 GBestimated | Open |
| UD-Q4_K_S | 179 GB | 179 GBestimated | Open |
| MXFP4_MOE | 185 GB | 186 GBestimated | Open |
| UD-Q4_K_M | 191 GB | 191 GBestimated | Open |
| UD-Q4_K_XL | 192 GB | 192 GBestimated | Open |
| UD-Q5_K_S | 216 GB | 217 GBestimated | Open |
| UD-Q5_K_M | 230 GB | 230 GBestimated | Open |
| UD-Q5_K_XL | 231 GB | 231 GBestimated | Open |
| UD-Q6_K | 257 GB | 257 GBestimated | Open |
| UD-Q6_K_XL | 281 GB | 282 GBestimated | Open |
| Q8_0 | 329 GB | 330 GBestimated | Open |
| UD-Q8_K_XL | 337 GB | 338 GBestimated | Open |
| BF16 | 620 GB | 620 GBestimated | Open |
Run It Anywhere
MiMo V2.5 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/MiMo-V2.5-GGUF:UD-IQ1_M - llama.cppMac, Windows, Linux
llama-server -hf unsloth/MiMo-V2.5-GGUF:UD-IQ1_M - Docker Model RunnerMac, Windows, Linux
docker model run hf.co/unsloth/MiMo-V2.5-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 97 GB | |
| 8 GB | None worth running | needs 97 GB | |
| 10 GB | None worth running | needs 97 GB | |
| 11 GB | None worth running | needs 97 GB | |
| 12 GB | None worth running | needs 97 GB | |
| 16 GB | None worth running | needs 97 GB | |
| 20 GB | None worth running | needs 97 GB | |
| 24 GB | None worth running | needs 97 GB | |
| 32 GB | None worth running | needs 97 GB | |
| 48 GB | None worth running | needs 97 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 | UD-IQ1_M | Too big | 107 GB | |
| M6 · 24 GB | UD-IQ1_M | Too big | 107 GB | |
| M6 · 32 GB | UD-IQ1_M | Too big | 107 GB | |
| M5 · 16 GB | UD-IQ1_M | Too big | 107 GB | |
| M5 · 24 GB | UD-IQ1_M | Too big | 107 GB | |
| M5 · 32 GB | UD-IQ1_M | Too big | 107 GB | |
| M5 Pro · 24 GB | UD-IQ1_M | Too big | 107 GB | |
| M5 Pro · 48 GB | UD-IQ1_M | Too big | 107 GB | |
| M5 Pro · 64 GB | UD-IQ1_M | Too big | 107 GB | |
| M5 Max · 36 GB | UD-IQ1_M | Too big | 107 GB | |
| M5 Max · 48 GB | UD-IQ1_M | Too big | 107 GB | |
| M5 Max · 64 GB | UD-IQ1_M | Too big | 107 GB | |
| M5 Max · 128 GB | UD-IQ2_XXS | Runs well | 100 GB | 66 |
| M5 Ultra · 96 GB | UD-IQ1_M | Too big | 107 GB | |
| M5 Ultra · 256 GB | UD-IQ4_NL | Runs great | 167 GB | 82 |
| M5 Ultra · 512 GB | Q8_0 | Runs great | 343 GB | 61 |
| M4 · 16 GB | UD-IQ1_M | Too big | 107 GB | |
| M4 · 24 GB | UD-IQ1_M | Too big | 107 GB | |
| M4 · 32 GB | UD-IQ1_M | Too big | 107 GB | |
| M4 Pro · 24 GB | UD-IQ1_M | Too big | 107 GB | |
| M4 Pro · 48 GB | UD-IQ1_M | Too big | 107 GB | |
| M4 Pro · 64 GB | UD-IQ1_M | Too big | 107 GB | |
| M4 Max · 36 GB | UD-IQ1_M | Too big | 107 GB | |
| M4 Max · 48 GB | UD-IQ1_M | Too big | 107 GB | |
| M4 Max · 64 GB | UD-IQ1_M | Too big | 107 GB | |
| M4 Max · 96 GB | UD-IQ1_M | Too big | 107 GB | |
| M4 Max · 128 GB | UD-IQ2_XXS | Runs well | 100 GB | 34 |
| M3 · 8 GB | UD-IQ1_M | Too big | 107 GB | |
| M3 · 16 GB | UD-IQ1_M | Too big | 107 GB | |
| M3 · 24 GB | UD-IQ1_M | Too big | 107 GB | |
| M3 Pro · 18 GB | UD-IQ1_M | Too big | 107 GB | |
| M3 Pro · 36 GB | UD-IQ1_M | Too big | 107 GB | |
| M3 Max · 36 GB | UD-IQ1_M | Too big | 107 GB | |
| M3 Max · 48 GB | UD-IQ1_M | Too big | 107 GB | |
| M3 Max · 64 GB | UD-IQ1_M | Too big | 107 GB | |
| M3 Max · 96 GB | UD-IQ1_M | Too big | 107 GB | |
| M3 Max · 128 GB | UD-IQ2_XXS | Runs well | 100 GB | 33 |
| M3 Ultra · 96 GB | UD-IQ1_M | Too big | 107 GB | |
| M3 Ultra · 256 GB | UD-IQ4_NL | Runs great | 167 GB | 38 |
| M3 Ultra · 512 GB | Q8_0 | Runs great | 343 GB | 31 |
| M2 · 8 GB | UD-IQ1_M | Too big | 107 GB | |
| M2 · 16 GB | UD-IQ1_M | Too big | 107 GB | |
| M2 · 24 GB | UD-IQ1_M | Too big | 107 GB | |
| M2 Pro · 16 GB | UD-IQ1_M | Too big | 107 GB | |
| M2 Pro · 32 GB | UD-IQ1_M | Too big | 107 GB | |
| M2 Max · 32 GB | UD-IQ1_M | Too big | 107 GB | |
| M2 Max · 64 GB | UD-IQ1_M | Too big | 107 GB | |
| M2 Max · 96 GB | UD-IQ1_M | Too big | 107 GB | |
| M2 Ultra · 64 GB | UD-IQ1_M | Too big | 107 GB | |
| M2 Ultra · 128 GB | UD-IQ2_XXS | Runs well | 100 GB | 44 |
| M2 Ultra · 192 GB | UD-IQ3_XXS | Runs great | 130 GB | 41 |
| M1 · 8 GB | UD-IQ1_M | Too big | 107 GB | |
| M1 · 16 GB | UD-IQ1_M | Too big | 107 GB | |
| M1 Pro · 16 GB | UD-IQ1_M | Too big | 107 GB | |
| M1 Pro · 32 GB | UD-IQ1_M | Too big | 107 GB | |
| M1 Max · 32 GB | UD-IQ1_M | Too big | 107 GB | |
| M1 Max · 64 GB | UD-IQ1_M | Too big | 107 GB | |
| M1 Ultra · 64 GB | UD-IQ1_M | Too big | 107 GB | |
| M1 Ultra · 128 GB | UD-IQ2_XXS | Runs well | 100 GB | 31 |
Writes is words a second, estimated from the Mac's memory speed and the model's size; how, and how wrong.
Information
- Maker
- Xiaomi
- Released
- April 2026
- Parameters
- 310B, 6.2B active
- Longest chat
- 1M tokens
- Reads pictures
- No
- Licence
- mit
- Downloads this month
- 3,624
- Likes
- 51
- Sizes
- 22, 93 to 620 GB
- Kind
- Maker's release
- Source
- XiaomiMiMo/MiMo-V2.5
Badge for the model card
Shows on MiMo V2.5'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.
