Volodymyr Kuleshov 🇺🇦
@volokuleshov
📢 Mercury 2.5 is here!
🚀 Since Mercury 2, usage has grown over an order of magnitude, with customers running latency-sensitive workloads across search, voice and coding agents.
Now: 40% more intelligence than Mercury 2, 1,100+ tok/s, lower price, 260K context + better agent
🚀 Since Mercury 2, usage has grown over an order of magnitude, with customers running latency-sensitive workloads across search, voice and coding agents.
Now: 40% more intelligence than Mercury 2, 1,100+ tok/s, lower price, 260K context + better agent
Stefano Ermon@StefanoErmon · Sep 8Today we're excited to announce Mercury 2.5
It’s the most capable diffusion LLM on the market. It is a 40% jump in intelligence over Mercury 2 and runs at over 1,100 tokens/sec on widely available @NVIDIAAI GPUs.
inceptionlabs.ai/blog/introduci…
It’s the most capable diffusion LLM on the market. It is a 40% jump in intelligence over Mercury 2 and runs at over 1,100 tokens/sec on widely available @NVIDIAAI GPUs.
inceptionlabs.ai/blog/introduci…
0:43 1 31