DeepSeek V3.1 Terminus
671.2B total, 37.7B active · 160k context · MIT License · released 2025-09-22
chatreasoningagenticcoding
What to run it on in Germany
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
Same structure as DeepSeek-V3; the self_attn.o_proj parameters do not conform to the UE8M0 FP8 scale format (known issue). Search agent uses an updated template and tool-set. Excludes 13.4B parameters of multi-token-prediction layers, which local runtimes do not load.
Questions
- What licence is DeepSeek V3.1 Terminus released under?
- MIT License, which allows commercial use.