DeepSeek R1 Zero
671.2B total, 37.7B active · 160k context · MIT License · released 2025-01-20
reasoningchatcoding
What to run it on in the US
Fully in memory at 64k context, priced at retailers today.
Nothing we price holds this model fully in memory.
All hardware that runs it
Everything we price, best value first. Two cards split the model by layers.
Nothing we price can run it at this context.
Memory needed
Weights, KV cache and runtime buffers at each context length (KV cache at fp16).
| Quant | File |
|---|
Run it
Copy a command for the runtime you use.
No published builds to run yet.
Notes
Trained with pure RL without SFT; the card notes endless repetition, poor readability and language mixing. Hugging Face Transformers is not directly supported; see the DeepSeek-V3 repo for running it locally. Excludes 13.4B parameters of multi-token-prediction layers, which local runtimes do not load.
Questions
- What licence is DeepSeek R1 Zero released under?
- MIT License, which allows commercial use.