Unverified70% confidenceBenchmarkExact time
Groq's LPU focuses on ultra-low latency inference and has achieved output speeds exceeding 500 tokens per second.
2
Sources
70%
Confidence
Medium-term (~90 days)
Relevance
8/22/2026
First Seen
Valid until: 11/20/2026
Sources
Related Claims
UnverifiedUltrafast can generate content at a speed of up to 750 tokens per second.70% similarUnverifiedOpen-weight models can achieve throughput of 420 to 2100 tokens/second on Groq LPUs and Cerebras wafer-scale clusters.68% similarUnverifiedUnder this configuration, the 35B model achieves a measured single-user peak speed of approximately 80 tokens/second, with concurrent throughput exceeding 500 tokens/second.65% similarUnverifiedSGLang using official NVFP4 weights with D-Spark speculative decoding achieved an average of approximately 173 tokens/second on Blackwell GPUs, approaching 200 for short tasks, while loading a 262k context window.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/785685API
curl https://kongchang.com/api/v1/knowledge/claims/785685MCP
get_claim(id=785685)