Inception releases Mercury 3, a diffusion language model with speeds of up to 1,068 tok/s
Inception Releases Mercury 3 Diffusion LLM at 1,068 Tokens per Second
AI BriefingInception releases Mercury 3, a diffusion language model that the company says achieves 1,068 tok/s on NVIDIA GPUs, has a 1M-token context window, and has over 40 times as many parameters as Mercury 1.
Also reported by 2 other sources
- Inception Releases Mercury 3 Diffusion Language Model, Claiming to Surpass GPT-6 Luna and Claude Haiku 5.5 on Some BenchmarksThe Decoder:AI News · 26 days ago
- Inception Labs releases Mercury 3, a diffusion large language model reaching 1068 tokens/secondInception Labs:Blog · 28 days ago
Source: MarkTechPost · marktechpost.com
Event follow-up2
View all event coverage- Inception Labs releases Mercury 3, a diffusion large language model reaching 1068 tokens/secondInception Labs:Blog · 28 days ago
- Inception's diffusion model Mercury 3 launches on OpenRouterOpenRouter · 28 days ago