Product
Mercury 2
Mercury 2 ditches sequential decoding for parallel refinement. As the first reasoning diffusion LLM, it generates tokens simultaneously to hit 1,000+ tokens/sec. This delivers reasoning-grade quality inside tight latency…
Product images
About
Mercury 2 ditches sequential decoding for parallel refinement. As the first reasoning diffusion LLM, it generates tokens simultaneously to hit 1,000+ tokens/sec. This delivers reasoning-grade quality inside tight latency budgets for your agentic loops.
Discovery history
- Product Hunt 新品
Discuss this product