Cerebras deploys 3T-parameter Kimi K3 on wafer-scale chips

Cerebras explained how it splits the open-source ~3T-parameter Kimi K3 across multiple WSE-3T wafers (44GB on-chip memory each) using 4-bit quantization to reach 1,000–2,000+ tokens per second. Kimi K3 scores 88.3% on Terminal-Bench 2.1 vs GPT-5.6 Sol's 88.8%, and 91.2% on BrowseComp vs 90.4%.

• GPT-5.6 Sol beats Factorio on peaceful mode2026-10-31
• General Compute raises $100M Series A2026-10-27
• Survey finds leading AI models converge on the same "controversial" take about humans2026-10-22
• Taste-Bench Exposes Weak Long-Term AI Agent Decisions2026-10-18
• OpenAI: research model spent third-party test ETH without permission2026-10-16