A 1T, 20B active chat model from Xiaomi.
- Rating
- 4.4
- Downloads
- 4.9K
- Likes
- 22
- Parameters
- 1T, 20B active
- Context
- 1M
- Licence
- mit
Too big for this Mac
Its smallest size needs 335 GB of memory, more than M4 · 16 GB can give it.
Ratings
4.4 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.
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.
MiMo V2.5 Pro runs well from a Mac with an M3 Ultra and 512 GB of memory. 2 of 59 Mac configurations run it well.
Compare with
The nearest models in size.
Sizes
From unsloth/MiMo-V2.5-Pro-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 | 304 GB | 304 GBestimated | Open |
| UD-IQ2_XXS | 317 GB | 318 GBestimated | Open |
| UD-IQ2_M | 317 GB | 318 GBestimated | Open |
| UD-Q2_K_XL | 338 GB | 339 GBestimated | Open |
| UD-IQ3_S | 378 GB | 378 GBestimated | Open |
| UD-IQ3_XXS | 413 GB | 413 GBestimated | Open |
| UD-Q3_K_M | 460 GB | 460 GBestimated | Open |
| UD-Q3_K_XL | 460 GB | 460 GBestimated | Open |
| UD-IQ4_XS | 491 GB | 491 GBestimated | Open |
| UD-IQ4_NL | 501 GB | 502 GBestimated | Open |
| UD-Q4_K_S | 589 GB | 589 GBestimated | Open |
| MXFP4_MOE | 611 GB | 611 GBestimated | Open |
| UD-Q4_K_M | 630 GB | 630 GBestimated | Open |
| UD-Q4_K_XL | 631 GB | 631 GBestimated | Open |
| UD-Q5_K_S | 713 GB | 714 GBestimated | Open |
| UD-Q5_K_M | 758 GB | 758 GBestimated | Open |
| UD-Q5_K_XL | 759 GB | 760 GBestimated | Open |
| UD-Q6_K | 847 GB | 847 GBestimated | Open |
| UD-Q6_K_XL | 928 GB | 929 GBestimated | Open |
| Q8_0 | 1088 GB | 1088 GBestimated | Open |
| UD-Q8_K_XL | 1101 GB | 1102 GBestimated | Open |
| BF16 | 2047 GB | 2047 GBestimated | Open |
Run It Anywhere
MiMo V2.5 Pro 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-Pro-GGUF:UD-IQ1_M - llama.cppMac, Windows, Linux
llama-server -hf unsloth/MiMo-V2.5-Pro-GGUF:UD-IQ1_M - Docker Model RunnerMac, Windows, Linux
docker model run hf.co/unsloth/MiMo-V2.5-Pro-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 318 GB | |
| 8 GB | None worth running | needs 318 GB | |
| 10 GB | None worth running | needs 318 GB | |
| 11 GB | None worth running | needs 318 GB | |
| 12 GB | None worth running | needs 318 GB | |
| 16 GB | None worth running | needs 318 GB | |
| 20 GB | None worth running | needs 318 GB | |
| 24 GB | None worth running | needs 318 GB | |
| 32 GB | None worth running | needs 318 GB | |
| 48 GB | None worth running | needs 318 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 | 335 GB | |
| M6 · 24 GB | UD-IQ1_M | Too big | 335 GB | |
| M6 · 32 GB | UD-IQ1_M | Too big | 335 GB | |
| M5 · 16 GB | UD-IQ1_M | Too big | 335 GB | |
| M5 · 24 GB | UD-IQ1_M | Too big | 335 GB | |
| M5 · 32 GB | UD-IQ1_M | Too big | 335 GB | |
| M5 Pro · 24 GB | UD-IQ1_M | Too big | 335 GB | |
| M5 Pro · 48 GB | UD-IQ1_M | Too big | 335 GB | |
| M5 Pro · 64 GB | UD-IQ1_M | Too big | 335 GB | |
| M5 Max · 36 GB | UD-IQ1_M | Too big | 335 GB | |
| M5 Max · 48 GB | UD-IQ1_M | Too big | 335 GB | |
| M5 Max · 64 GB | UD-IQ1_M | Too big | 335 GB | |
| M5 Max · 128 GB | UD-IQ1_M | Too big | 335 GB | |
| M5 Ultra · 96 GB | UD-IQ1_M | Too big | 335 GB | |
| M5 Ultra · 256 GB | UD-IQ1_M | Too big | 335 GB | |
| M5 Ultra · 512 GB | UD-IQ3_S | Runs well | 409 GB | 40 |
| M4 · 16 GB | UD-IQ1_M | Too big | 335 GB | |
| M4 · 24 GB | UD-IQ1_M | Too big | 335 GB | |
| M4 · 32 GB | UD-IQ1_M | Too big | 335 GB | |
| M4 Pro · 24 GB | UD-IQ1_M | Too big | 335 GB | |
| M4 Pro · 48 GB | UD-IQ1_M | Too big | 335 GB | |
| M4 Pro · 64 GB | UD-IQ1_M | Too big | 335 GB | |
| M4 Max · 36 GB | UD-IQ1_M | Too big | 335 GB | |
| M4 Max · 48 GB | UD-IQ1_M | Too big | 335 GB | |
| M4 Max · 64 GB | UD-IQ1_M | Too big | 335 GB | |
| M4 Max · 96 GB | UD-IQ1_M | Too big | 335 GB | |
| M4 Max · 128 GB | UD-IQ1_M | Too big | 335 GB | |
| M3 · 8 GB | UD-IQ1_M | Too big | 335 GB | |
| M3 · 16 GB | UD-IQ1_M | Too big | 335 GB | |
| M3 · 24 GB | UD-IQ1_M | Too big | 335 GB | |
| M3 Pro · 18 GB | UD-IQ1_M | Too big | 335 GB | |
| M3 Pro · 36 GB | UD-IQ1_M | Too big | 335 GB | |
| M3 Max · 36 GB | UD-IQ1_M | Too big | 335 GB | |
| M3 Max · 48 GB | UD-IQ1_M | Too big | 335 GB | |
| M3 Max · 64 GB | UD-IQ1_M | Too big | 335 GB | |
| M3 Max · 96 GB | UD-IQ1_M | Too big | 335 GB | |
| M3 Max · 128 GB | UD-IQ1_M | Too big | 335 GB | |
| M3 Ultra · 96 GB | UD-IQ1_M | Too big | 335 GB | |
| M3 Ultra · 256 GB | UD-IQ1_M | Too big | 335 GB | |
| M3 Ultra · 512 GB | UD-IQ3_S | Runs well | 409 GB | 21 |
| M2 · 8 GB | UD-IQ1_M | Too big | 335 GB | |
| M2 · 16 GB | UD-IQ1_M | Too big | 335 GB | |
| M2 · 24 GB | UD-IQ1_M | Too big | 335 GB | |
| M2 Pro · 16 GB | UD-IQ1_M | Too big | 335 GB | |
| M2 Pro · 32 GB | UD-IQ1_M | Too big | 335 GB | |
| M2 Max · 32 GB | UD-IQ1_M | Too big | 335 GB | |
| M2 Max · 64 GB | UD-IQ1_M | Too big | 335 GB | |
| M2 Max · 96 GB | UD-IQ1_M | Too big | 335 GB | |
| M2 Ultra · 64 GB | UD-IQ1_M | Too big | 335 GB | |
| M2 Ultra · 128 GB | UD-IQ1_M | Too big | 335 GB | |
| M2 Ultra · 192 GB | UD-IQ1_M | Too big | 335 GB | |
| M1 · 8 GB | UD-IQ1_M | Too big | 335 GB | |
| M1 · 16 GB | UD-IQ1_M | Too big | 335 GB | |
| M1 Pro · 16 GB | UD-IQ1_M | Too big | 335 GB | |
| M1 Pro · 32 GB | UD-IQ1_M | Too big | 335 GB | |
| M1 Max · 32 GB | UD-IQ1_M | Too big | 335 GB | |
| M1 Max · 64 GB | UD-IQ1_M | Too big | 335 GB | |
| M1 Ultra · 64 GB | UD-IQ1_M | Too big | 335 GB | |
| M1 Ultra · 128 GB | UD-IQ1_M | Too big | 335 GB |
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
- 1T, 20B active
- Longest chat
- 1M tokens
- Reads pictures
- No
- Licence
- mit
- Downloads this month
- 4,864
- Likes
- 22
- Sizes
- 22, 304 to 2047 GB
- Kind
- Maker's release
- Source
- XiaomiMiMo/MiMo-V2.5-Pro
Badge for the model card
Shows on MiMo V2.5 Pro'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.
