Hugging FaceBuilt for long, many-step tasks that need a lot of text held in view at once.
- Rating
- 4.7
- Downloads
- 94K
- Parameters
- 1.6T, 49B active
- Context
- 1M
- Download
- 850 to 873 GB
- Commercial use
- Yes
Too big for this Mac
Its smallest size needs 851 GB of memory, more than M4 · 16 GB can give it.
About
This is the official release, and it replaces the earlier preview version. The makers designed two compressed ways of reading text to make long inputs more efficient.
How it compares
In LM Arena's public vote for text, it places 5th of 62 open models.
For coding, LM Arena's public vote places it 7th of 59 open models.
Good to know
It was trained on more than 32 trillion pieces of text.
At its longest input, the maker says it needs about a quarter of the computing DeepSeek V3.2 needs.
It has a smaller sibling, DeepSeek V4 Flash, about a sixth of its size.
Sources: deepseek-ai/DeepSeek-V4-Pro-0813 model card, DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence, Outmake's speed estimates, LM Arena and Hugging Face. Every line comes from one of these.
Ratings
4.7 out of 5, from how people voted on its answers.
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.
Good at
Licence
MIT. Commercial use: yes. The maker's page has the full terms.
DeepSeek V4 Pro does not run well on any Mac Outmake lists; its smallest size needs more memory than the largest configuration has. 0 of 59 Mac configurations run it well.
Compare with
The nearest models in size, judged for the same Mac.
Sizes
| Size | Download | Memory at 8K | Memory at 32K | Open |
|---|---|---|---|---|
| UD-Q4_K_XLBalanced | 850 GB | 850 GB | 850 GB | Open |
| UD-Q8_K_XLBest | 873 GB | 872 GB | 873 GB | Open |
Memory is what llama.cpp's own calculator reported for each size when the catalog was built, with the app's settings. Smaller, Balanced and Best are the three sizes the store names.
Run It Anywhere
DeepSeek V4 Pro is an open model, so any app that runs GGUF files can run it. These take the UD-Q4_K_XL 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/DeepSeek-V4-Pro-0813-GGUF:UD-Q4_K_XL - llama.cppMac, Windows, Linux
llama-server -hf unsloth/DeepSeek-V4-Pro-0813-GGUF:UD-Q4_K_XL - Docker Model RunnerMac, Windows, Linux
docker model run hf.co/unsloth/DeepSeek-V4-Pro-0813-GGUF:UD-Q4_K_XL
On a PC Graphics Card
| Video memory | Largest size that fits | Download | Memory at 8K |
|---|---|---|---|
| 6 GB | None worth running | needs 850 GB | |
| 8 GB | None worth running | needs 850 GB | |
| 10 GB | None worth running | needs 850 GB | |
| 11 GB | None worth running | needs 850 GB | |
| 12 GB | None worth running | needs 850 GB | |
| 16 GB | None worth running | needs 850 GB | |
| 20 GB | None worth running | needs 850 GB | |
| 24 GB | None worth running | needs 850 GB | |
| 32 GB | None worth running | needs 850 GB | |
| 48 GB | None worth running | needs 850 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. The memory is what llama.cpp's own calculator reported for each size; 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 | Reads |
|---|---|---|---|---|---|
| M6 · 16 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M6 · 24 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M6 · 32 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M5 · 16 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M5 · 24 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M5 · 32 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M5 Pro · 24 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M5 Pro · 48 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M5 Pro · 64 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M5 Max · 36 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M5 Max · 48 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M5 Max · 64 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M5 Max · 128 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M5 Ultra · 96 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M5 Ultra · 256 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M5 Ultra · 512 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M4 · 16 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M4 · 24 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M4 · 32 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M4 Pro · 24 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M4 Pro · 48 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M4 Pro · 64 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M4 Max · 36 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M4 Max · 48 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M4 Max · 64 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M4 Max · 96 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M4 Max · 128 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M3 · 8 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M3 · 16 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M3 · 24 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M3 Pro · 18 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M3 Pro · 36 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M3 Max · 36 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M3 Max · 48 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M3 Max · 64 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M3 Max · 96 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M3 Max · 128 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M3 Ultra · 96 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M3 Ultra · 256 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M3 Ultra · 512 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M2 · 8 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M2 · 16 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M2 · 24 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M2 Pro · 16 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M2 Pro · 32 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M2 Max · 32 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M2 Max · 64 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M2 Max · 96 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M2 Ultra · 64 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M2 Ultra · 128 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M2 Ultra · 192 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M1 · 8 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M1 · 16 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M1 Pro · 16 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M1 Pro · 32 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M1 Max · 32 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M1 Max · 64 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M1 Ultra · 64 GB | UD-Q4_K_XL | Too big | 851 GB | ||
| M1 Ultra · 128 GB | UD-Q4_K_XL | Too big | 851 GB |
Writes and reads are words a second (a token is about three quarters of a word), 4K tokens into a chat, estimated unless marked measured. The size is the one the store offers that Mac. Constants fitted October 11, 2026; how, and how wrong.
Badge for the model card
Shows on DeepSeek V4 Pro's Hugging Face card which Macs run it well, linked to this page. It updates every morning.
Sizes and files are read from unsloth/DeepSeek-V4-Pro-0813-GGUF on Hugging Face and checked every morning. The rating is the model's score on the LM Arena text leaderboard (CC BY 4.0), where people vote between two answers without knowing which model wrote which. Catalog of November 4, 2026.