Model family
DeepSeek v3 / R1
MoE
Listed checkpoints
Notes
Checkpoints listed here identify models in this family. Check each recipe for inference verification, hardware measurements, and requirements before running it.
Feature matrix
| Runtimes | generateserve |
|---|---|
| Backends | CUDA:supportedMetal:supportedROCm:partially supported |
| Tensor parallel | no |
| Pipeline parallel | yes |
| Drafters | none |
| KV modes | fp16 |
| Input modalities | text |
| Output | tokens |
| Model types | deepseek_v3kimi_k2joyai_llm_flash |
Recipes in this family
Choose hardware to estimate fit.