Platform Profile
Groq
Groq builds specialized inference hardware and software for extremely fast AI responses.
Role
Inference speed
Stack
LPUs
Status
Active
Groq focuses on making high-speed inference widely accessible.
Related Coverage
- Nvidia Puts Groq 3 LPX Inference Racks Into Full Production
On August 24, 2026, Nvidia said Groq 3 LPX—the interactive inference accelerator that extends Vera Rubin—is in full production. Artificial Analysis measured 3,431 output tokens per second on Gemma 4 31B at 100K context. Nebius is the first named cloud; Groq will follow with Dell. Each LPX rack holds 256 LP30 accelerators.
- Groq Raises $350 Million at $3.5 Billion as It Rebuilds as a Neocloud
On August 17, 2026, Groq announced a $350 million Series A led by Disruptive with planned Nvidia participation, valuing the inference operator at $3.5 billion—about half its 2025 peak after Nvidia’s licensing deal hired away founder Jonathan Ross—and bringing 2026 capital to $1 billion as it targets 200+ MW in 2027.