Expired65% confidenceFactTime unknown
Mercury 2 achieved a measured generation speed of over 1,000 tokens per second.
3
Sources
65%
Confidence
Medium-term (~90 days)
Relevance
5/31/2026
First Seen
Valid until: 8/29/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedHalo's prefill result of 650 tokens/s is nearly double the speed measured for the same chip last year, with the improvement stemming from AMD contributing code to upstream open-source projects such as llama.cpp to advance the maturity of the ROCm ecosystem.60% similarUnverifiedA sandbox engine with 8 million parameters (8.3M) achieves a decoding speed of approximately 2,000 tokens/second on a 6-core desktop CPU released in 2019.59% similarUnverifiedIn prefill speed tests, Halo achieved approximately 650 tokens/s while Spark achieved approximately 2000 tokens/s, with Spark being nearly three times faster.56% similarUnverifiedBased on the MLX framework, top-configured Mac models can achieve a generation speed of approximately 20 tokens/second when running the Llama-3-70B quantized model.56% similarUnverifiedIn a controlled test, the 35B model ran at approximately 100 tokens/second (Mac Studio), roughly five times the 9B model's 16 tokens/second56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/14048API
curl https://kongchang.com/api/v1/knowledge/claims/14048MCP
get_claim(id=14048)