Unverified50% confidenceDecision RuleExact time
The author considers a model usable only if it achieves at least 10 tokens per second.
1
Sources
50%
Confidence
Long-term
Relevance
10/11/2026
First Seen
Sources
Related Claims
UnverifiedThe 12-billion-parameter Gemma dense model achieved a measured speed of just over 10 tokens/second.73% similarUnverifiedAt a price of around 1,000+ USD, the Mac mini achieves a local large language model inference speed of approximately 10 tokens per second.70% similarUnverifiedWith all three optimizations stacked, generation speed stabilizes at 9 to 10 tokens per second, but time-to-first-token for a 10,000-character long document still requires approximately 329 seconds.69% similarUnverifiedThis Clash Royale RL simulator requires only approximately 10 milliseconds per match.68% similarUnverifiedHugo官方基准测试显示处理10000个页面仅需约7秒66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/999472API
curl https://kongchang.com/api/v1/knowledge/claims/999472MCP
get_claim(id=999472)