Unverified50% confidenceBenchmarkExact time
On M-series Macs, the gemma3:1b model has response times of approximately 4 seconds (p50) and 6.7 seconds (p95).
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/16/2026
First Seen
Valid until: 2/14/2027
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.72% similarUnverifiedWhen generating images using a 4-billion-parameter distilled model, the Mac mini produces approximately one image every 12 seconds (about 5 per minute), while the Mac Studio produces approximately one image every 2 seconds (about 29 per minute).70% similarUnverifiedIn a test with 1,000 candidate options, CLM took approximately 44 milliseconds, while a generative model required 579 milliseconds.69% similarVerifiedRunning 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).69% similarUnverifiedSnapshot restoration time is now counted in the creation phase, and creation time has increased by about 50 milliseconds at p50; for uncached snapshots, the increase may be larger68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1174875API
curl https://kongchang.com/api/v1/knowledge/claims/1174875MCP
get_claim(id=1174875)