Nvidia Claims Groq 3 LPX 4x Faster Than Cerebras, But Needs 64 Accelerators
The Decoder · rss · 2026-08-25
Nvidia is moving its Groq 3 LPX inference chip into full production, reporting 3,400 tokens per second on Gemma 4 31B, four times faster than Cerebras. However, The Register notes Nvidia needs at least 64 accelerators to achieve this, while Cerebras needs only one or two. How the architecture scales with large MoE models remains an open question.
More from Infra
- SK Hynix ties new US plant to looser chip equipment exports to China, sources say — pstAsiatech · 2026-10-15
- Perplexity's new embedding models: index with a 9B model, search with 0.6B — antoine_chaffin · 2026-10-15
- Unsloth ships GGUF quants for Nemotron 3.5: Bolt-74B runs in 24GB RAM — danielhanchen · 2026-10-15
- vLLM-Omni ships Day-0 serving for FLUX 3 Image Klein with BF16, FP8, NVFP4 support — vllm_project · 2026-10-15
- NVIDIA's Nemotron 3.5 Super VL lands training and inference support on Applied Compute — ypatil125 · 2026-10-15
- CoreWeave bond yield tops 16% as loans outlast customer contracts by ~2 years — tengyanAI · 2026-10-15