Expired50% confidenceBenchmarkExact time
Running the 2B model locally to translate Markdown text into English achieved a speed of 53.2 tokens/second, with the entire passage taking approximately 0.44 seconds.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/3/2026
First Seen
Valid until: 10/17/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedIn this test, the model's output speed in short-context scenarios is approximately 20 tokens/second, dropping to approximately 13 tokens/second for contexts of 200K+.68% similarUnverifiedWhen Tidy processes short text (100–500 tokens), inference latency is approximately 1–2 seconds for initial loading plus 200–800 milliseconds of computation, with continuous use impacting battery life by less than 5% per hour.68% similarUnverifiedLocal model inference speed is approximately 1–10 tokens/second, while cloud-based APIs can reach 50–150 tokens/second.67% similarUnverifiedIt is generally considered that single-concurrency output above 100 tokens/second is sufficient to achieve a smooth typewriter effect, and at approximately 200 tokens/second, generating a 2,000-character long text takes only about 10 seconds.67% similarUnverifiedEnd-to-end models have reduced average latency in speech translation from the 2–3 seconds of traditional pipelines to approximately 300 milliseconds.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/970304API
curl https://kongchang.com/api/v1/knowledge/claims/970304MCP
get_claim(id=970304)