DeepSeek-MoE
DeepSeek·
LLMsopen-weightcloud + localEdge / Consumer
Overview
Mixture-of-Experts architecture.
Capabilities and innovations
MoE efficiencyHigh throughputCost effectiveMoE EfficiencyCost-effective TrainingHigh Throughput
Benchmarks
No benchmark values are recorded for this model.
- GPQA Diamond: not reported by the vendor
- Humanity’s Last Exam (no tools): not reported by the vendor
- SWE-bench Verified: not reported by the vendor
- SWE-bench Pro: benchmark did not exist at release
- MMLU: not reported by the vendor
- MMLU-Pro: benchmark did not exist at release
- Terminal-Bench 2.x: benchmark did not exist at release
- MMMU-Pro: benchmark did not exist at release
Architecture and hardware
- Parameters
- 14.6B total, 2.8B active per token (MoE)
- Estimated VRAM at Q4
- ~9 GB, Edge / Consumer class
Links
More from DeepSeek
Data curated by AI Model Timeline. See the methodology for admission criteria, benchmark eras and source priority.