Unverified50% confidenceBenchmarkExact time
Running a 27B model on M1 Max with a 32,000-token prompt requires waiting more than 500 seconds before the first character is output, whereas the M5 Max takes less than one minute (approximately 40 seconds with optimized software).
1
Sources
50%
Confidence
Long-term
Relevance
10/5/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn the time-to-first-token test on a 70-billion-parameter model, the M3 Ultra took 31.6 seconds while the M5 Ultra took only 7.7 seconds, achieving approximately 4.1x, close to Apple's claimed 4.3x.78% similarVerifiedOn a T4 GPU, Laya takes 33 milliseconds per single question, and batch processing can compress that to 7 milliseconds75% similarUnverifiedIn a test with 1,000 candidate options, CLM took approximately 44 milliseconds, while a generative model required 579 milliseconds.74% similarUnverifiedA 3-billion-parameter Llama takes 1 to 3 seconds per call on CPU, while a 70B model takes 40 seconds per call.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/977845API
curl https://kongchang.com/api/v1/knowledge/claims/977845MCP
get_claim(id=977845)