Unverified50% confidenceBenchmarkExact time
In benchmark testing of prefilling a 2000-token file, the speed under a 16k context increased from 109 tok/s on Mac alone to 157 tok/s on Mac+iPhone (+44%).
1
Sources
50%
Confidence
Long-term
Relevance
10/2/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedOn a 128GB MacBook Pro M3 Max, independent benchmarks show DS4 achieving a generation speed of 26.68 tokens per second.73% similarUnverified27B稠密模型在24GB M4 Pro Mac mini上使用4-bit量化可以运行，速度约为11 tok/s71% similarUnverifiedThe Mac Studio M2 Ultra typically consumes between 100 and 150 W at full inference load, while a workstation equipped with dual RTX 4090 cards easily exceeds 800 W of total system power consumption.70% similarUnverifiedLing 3.0 Tiny achieves an inference speed of approximately 86–90 tokens per second on a MacBook with M4 Pro, with a peak memory usage of approximately 8.34 GiB under an 8K context.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/968228API
curl https://kongchang.com/api/v1/knowledge/claims/968228MCP
get_claim(id=968228)