DeepSeek Math V2
672B total, 38.5B active · 160k context · Apache License 2.0 · released 2025-11-27
reasoning
What to run it on in the US
Fully in memory at 32k 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
Built on DeepSeek-V3.2-Exp-Base; inference support is via the DeepSeek-V3.2-Exp GitHub repository. Focused on theorem proving and self-verifiable mathematical reasoning. Sparse or compressed attention: KV read per token is estimated as full attention. Excludes 13.4B parameters of multi-token-prediction layers, which local runtimes do not load.
Questions
- What licence is DeepSeek Math V2 released under?
- Apache License 2.0, which allows commercial use.