Hugging FaceA 1T, 52B active chat model from Mistral AI that reads pictures as well as text.
- Downloads
- 20K
- Likes
- 71
- Parameters
- 1T, 52B active
- Context
- 1M
- Licence
- other
Too big for this Mac
Its smallest size needs 283 GB of memory, more than M4 · 16 GB can give it.
Mistral Large 4 1T A52B 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/Mistral-Large-4-1T-A52B-GGUF on Hugging Face. A smaller size is a smaller download and a little less accurate.
| Size | Download | Memory at 8K | Get |
|---|---|---|---|
| UD-IQ1_S | 233 GB | 234 GBestimated | Open |
| UD-IQ1_M | 260 GB | 260 GBestimated | Open |
| UD-IQ2_XXS | 302 GB | 303 GBestimated | Open |
| UD-Q2_K_XL | 378 GB | 379 GBestimated | Open |
| UD-IQ3_XXS | 424 GB | 424 GBestimated | Open |
| UD-Q3_K_XL | 493 GB | 493 GBestimated | Open |
| UD-Q4_K_XL | 605 GB | 605 GBestimated | Open |
| UD-Q5_K_XL | 784 GB | 784 GBestimated | Open |
| UD-Q6_K_XL | 890 GB | 891 GBestimated | Open |
| Q8_0 | 1115 GB | 1116 GBestimated | Open |
| BF16 | 2099 GB | 2099 GBestimated | Open |
Run It Anywhere
Mistral Large 4 1T A52B is an open model, so any app that runs GGUF files can run it. These take the UD-IQ1_S 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/Mistral-Large-4-1T-A52B-GGUF:UD-IQ1_S - llama.cppMac, Windows, Linux
llama-server -hf unsloth/Mistral-Large-4-1T-A52B-GGUF:UD-IQ1_S - Docker Model RunnerMac, Windows, Linux
docker model run hf.co/unsloth/Mistral-Large-4-1T-A52B-GGUF:UD-IQ1_S
On a PC Graphics Card
| Video memory | Largest size that fits | Download | Memory at 8K |
|---|---|---|---|
| 6 GB | None worth running | needs 379 GB | |
| 8 GB | None worth running | needs 379 GB | |
| 10 GB | None worth running | needs 379 GB | |
| 11 GB | None worth running | needs 379 GB | |
| 12 GB | None worth running | needs 379 GB | |
| 16 GB | None worth running | needs 379 GB | |
| 20 GB | None worth running | needs 379 GB | |
| 24 GB | None worth running | needs 379 GB | |
| 32 GB | None worth running | needs 379 GB | |
| 48 GB | None worth running | needs 379 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 | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M6 · 24 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M6 · 32 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M5 · 16 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M5 · 24 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M5 · 32 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M5 Pro · 24 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M5 Pro · 48 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M5 Pro · 64 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M5 Max · 36 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M5 Max · 48 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M5 Max · 64 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M5 Max · 128 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M5 Ultra · 96 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M5 Ultra · 256 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M5 Ultra · 512 GB | Q2_K | Runs well | 406 GB | 20 |
| M4 · 16 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M4 · 24 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M4 · 32 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M4 Pro · 24 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M4 Pro · 48 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M4 Pro · 64 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M4 Max · 36 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M4 Max · 48 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M4 Max · 64 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M4 Max · 96 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M4 Max · 128 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M3 · 8 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M3 · 16 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M3 · 24 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M3 Pro · 18 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M3 Pro · 36 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M3 Max · 36 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M3 Max · 48 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M3 Max · 64 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M3 Max · 96 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M3 Max · 128 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M3 Ultra · 96 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M3 Ultra · 256 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M3 Ultra · 512 GB | Q2_K | Runs well | 406 GB | 12 |
| M2 · 8 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M2 · 16 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M2 · 24 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M2 Pro · 16 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M2 Pro · 32 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M2 Max · 32 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M2 Max · 64 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M2 Max · 96 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M2 Ultra · 64 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M2 Ultra · 128 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M2 Ultra · 192 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M1 · 8 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M1 · 16 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M1 Pro · 16 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M1 Pro · 32 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M1 Max · 32 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M1 Max · 64 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M1 Ultra · 64 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB | |
| M1 Ultra · 128 GB | Mistral-Large-4-1T-A52B-Mix-256G | Too big | 283 GB |
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
- Mistral AI
- Released
- September 2026
- Parameters
- 1T, 52B active
- Longest chat
- 1M tokens
- Reads pictures
- Yes
- Licence
- other
- Downloads this month
- 20,051
- Likes
- 71
- Sizes
- 11, 233 to 2099 GB
- Kind
- Maker's release
Badge for the model card
Shows on Mistral Large 4 1T A52B'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.