Hugging FaceA 309B, 9.2B active chat model from Xiaomi.
- Rating
- 3.7
- Downloads
- 21K
- Likes
- 33
- Parameters
- 309B, 9.2B active
- Context
- 256K
- Licence
- mit
Too big for this Mac
Its smallest size needs 81 GB of memory, more than M4 · 16 GB can give it.
Ratings
3.7 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 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.
- MiMo V2.6 Flash RLXiaomi · 47K downloadsToo big for this Mac · 108 GB
- MiMo V2.5Xiaomi · 3.6K downloads · Arena 1434Too big for this Mac · 93 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-Flash-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 | 78 GB | 78 GBestimated | Open |
| UD-IQ1_S | 87 GB | 87 GBestimated | Open |
| UD-IQ1_M | 94 GB | 94 GBestimated | Open |
| UD-IQ2_XXS | 102 GB | 102 GBestimated | Open |
| UD-IQ2_M | 107 GB | 107 GBestimated | Open |
| Q2_K | 112 GB | 113 GBestimated | Open |
| Q2_K_L | 112 GB | 113 GBestimated | Open |
| UD-Q2_K_XL | 116 GB | 117 GBestimated | Open |
| UD-IQ3_XXS | 127 GB | 128 GBestimated | Open |
| Q3_K_S | 133 GB | 133 GBestimated | Open |
| UD-Q3_K_XL | 137 GB | 137 GBestimated | Open |
| Q3_K_M | 147 GB | 148 GBestimated | Open |
| IQ4_XS | 164 GB | 165 GBestimated | Open |
| IQ4_NL | 174 GB | 174 GBestimated | Open |
| Q4_0 | 175 GB | 175 GBestimated | Open |
| Q4_K_S | 175 GB | 176 GBestimated | Open |
| UD-Q4_K_XL | 178 GB | 178 GBestimated | Open |
| Q4_K_M | 187 GB | 187 GBestimated | Open |
| Q4_1 | 193 GB | 194 GBestimated | Open |
| Q5_K_S | 213 GB | 213 GBestimated | Open |
| Q5_K_M | 219 GB | 219 GBestimated | Open |
| UD-Q5_K_XL | 220 GB | 220 GBestimated | Open |
| Q6_K | 253 GB | 254 GBestimated | Open |
| UD-Q6_K_XL | 263 GB | 264 GBestimated | Open |
| Q8_0 | 328 GB | 328 GBestimated | Open |
| UD-Q8_K_XL | 354 GB | 354 GBestimated | Open |
| BF16 | 618 GB | 618 GBestimated | Open |
Run It Anywhere
MiMo V2 Flash 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/MiMo-V2-Flash-GGUF:UD-TQ1_0 - llama.cppMac, Windows, Linux
llama-server -hf unsloth/MiMo-V2-Flash-GGUF:UD-TQ1_0 - Docker Model RunnerMac, Windows, Linux
docker model run hf.co/unsloth/MiMo-V2-Flash-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 107 GB | |
| 8 GB | None worth running | needs 107 GB | |
| 10 GB | None worth running | needs 107 GB | |
| 11 GB | None worth running | needs 107 GB | |
| 12 GB | None worth running | needs 107 GB | |
| 16 GB | None worth running | needs 107 GB | |
| 20 GB | None worth running | needs 107 GB | |
| 24 GB | None worth running | needs 107 GB | |
| 32 GB | None worth running | needs 107 GB | |
| 48 GB | None worth running | needs 107 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-TQ1_0 | Too big | 81 GB | |
| M6 · 24 GB | UD-TQ1_0 | Too big | 81 GB | |
| M6 · 32 GB | UD-TQ1_0 | Too big | 81 GB | |
| M5 · 16 GB | UD-TQ1_0 | Too big | 81 GB | |
| M5 · 24 GB | UD-TQ1_0 | Too big | 81 GB | |
| M5 · 32 GB | UD-TQ1_0 | Too big | 81 GB | |
| M5 Pro · 24 GB | UD-TQ1_0 | Too big | 81 GB | |
| M5 Pro · 48 GB | UD-TQ1_0 | Too big | 81 GB | |
| M5 Pro · 64 GB | UD-TQ1_0 | Too big | 81 GB | |
| M5 Max · 36 GB | UD-TQ1_0 | Too big | 81 GB | |
| M5 Max · 48 GB | UD-TQ1_0 | Too big | 81 GB | |
| M5 Max · 64 GB | UD-TQ1_0 | Too big | 81 GB | |
| M5 Max · 128 GB | UD-IQ1_M | Runs well | 97 GB | 54 |
| M5 Ultra · 96 GB | UD-TQ1_0 | Too big | 81 GB | |
| M5 Ultra · 256 GB | Q4_0 | Runs great | 175 GB | 70 |
| M5 Ultra · 512 GB | Q8_0 | Runs great | 332 GB | 46 |
| M4 · 16 GB | UD-TQ1_0 | Too big | 81 GB | |
| M4 · 24 GB | UD-TQ1_0 | Too big | 81 GB | |
| M4 · 32 GB | UD-TQ1_0 | Too big | 81 GB | |
| M4 Pro · 24 GB | UD-TQ1_0 | Too big | 81 GB | |
| M4 Pro · 48 GB | UD-TQ1_0 | Too big | 81 GB | |
| M4 Pro · 64 GB | UD-TQ1_0 | Too big | 81 GB | |
| M4 Max · 36 GB | UD-TQ1_0 | Too big | 81 GB | |
| M4 Max · 48 GB | UD-TQ1_0 | Too big | 81 GB | |
| M4 Max · 64 GB | UD-TQ1_0 | Too big | 81 GB | |
| M4 Max · 96 GB | UD-TQ1_0 | Too big | 81 GB | |
| M4 Max · 128 GB | UD-IQ1_M | Runs well | 97 GB | 31 |
| M3 · 8 GB | UD-TQ1_0 | Too big | 81 GB | |
| M3 · 16 GB | UD-TQ1_0 | Too big | 81 GB | |
| M3 · 24 GB | UD-TQ1_0 | Too big | 81 GB | |
| M3 Pro · 18 GB | UD-TQ1_0 | Too big | 81 GB | |
| M3 Pro · 36 GB | UD-TQ1_0 | Too big | 81 GB | |
| M3 Max · 36 GB | UD-TQ1_0 | Too big | 81 GB | |
| M3 Max · 48 GB | UD-TQ1_0 | Too big | 81 GB | |
| M3 Max · 64 GB | UD-TQ1_0 | Too big | 81 GB | |
| M3 Max · 96 GB | UD-TQ1_0 | Too big | 81 GB | |
| M3 Max · 128 GB | UD-IQ1_M | Runs well | 97 GB | 29 |
| M3 Ultra · 96 GB | UD-TQ1_0 | Too big | 81 GB | |
| M3 Ultra · 256 GB | Q4_0 | Runs great | 175 GB | 36 |
| M3 Ultra · 512 GB | Q8_0 | Runs great | 332 GB | 25 |
| M2 · 8 GB | UD-TQ1_0 | Too big | 81 GB | |
| M2 · 16 GB | UD-TQ1_0 | Too big | 81 GB | |
| M2 · 24 GB | UD-TQ1_0 | Too big | 81 GB | |
| M2 Pro · 16 GB | UD-TQ1_0 | Too big | 81 GB | |
| M2 Pro · 32 GB | UD-TQ1_0 | Too big | 81 GB | |
| M2 Max · 32 GB | UD-TQ1_0 | Too big | 81 GB | |
| M2 Max · 64 GB | UD-TQ1_0 | Too big | 81 GB | |
| M2 Max · 96 GB | UD-TQ1_0 | Too big | 81 GB | |
| M2 Ultra · 64 GB | UD-TQ1_0 | Too big | 81 GB | |
| M2 Ultra · 128 GB | UD-IQ1_M | Runs well | 97 GB | 41 |
| M2 Ultra · 192 GB | UD-IQ3_XXS | Runs great | 131 GB | 36 |
| M1 · 8 GB | UD-TQ1_0 | Too big | 81 GB | |
| M1 · 16 GB | UD-TQ1_0 | Too big | 81 GB | |
| M1 Pro · 16 GB | UD-TQ1_0 | Too big | 81 GB | |
| M1 Pro · 32 GB | UD-TQ1_0 | Too big | 81 GB | |
| M1 Max · 32 GB | UD-TQ1_0 | Too big | 81 GB | |
| M1 Max · 64 GB | UD-TQ1_0 | Too big | 81 GB | |
| M1 Ultra · 64 GB | UD-TQ1_0 | Too big | 81 GB | |
| M1 Ultra · 128 GB | UD-IQ1_M | Runs well | 97 GB | 30 |
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
- December 2025
- Parameters
- 309B, 9.2B active
- Longest chat
- 256K tokens
- Reads pictures
- No
- Licence
- mit
- Downloads this month
- 20,907
- Likes
- 33
- Sizes
- 27, 78 to 618 GB
- Kind
- Maker's release
- Source
- XiaomiMiMo/MiMo-V2-Flash
Badge for the model card
Shows on MiMo V2 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.