DeepSeek V3.2 Speciale
672B total, 38.5B active · 160k context · MIT License · released 2025-11-28
reasoningcoding
What to run it on in the US
Fully in memory at 8k 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
Speciale is designed exclusively for deep reasoning and does not support tool calling. No Jinja chat template is included; use the provided Python encoding scripts. 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 V3.2 Speciale released under?
- MIT License, which allows commercial use.