Unverified50% confidenceBenchmarkExact time
MiniCPM-V 4.7 35B-A3B achieves a decoding speed of 13+ tokens/s on the iPhone 17 Pro Max.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/12/2026
First Seen
Valid until: 10/26/2026
Sources
Related Entities
Related Claims
UnverifiedPrismML的Bonsai技术让27B参数模型在iPhone 17 Pro上以约11 tokens/秒的速度运行72% 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.71% similarUnverified在配备96GB显存的M2 Max上以1-bit精度运行时，简单任务生成速度稳定在约28-30 tokens/秒71% similarUnverifiedOn an RTX 5090, Muse Glimmer runs at 75 tokens/second without speculative decoding, and reaches 233 tokens/second when paired with a speculative decoding model71% similarUnverifiedWith a 5070 12 GB GPU paired with 64 GB of memory, speed can reach 93 tokens/s in short chat scenarios and 74 tokens/s for 128K long contexts.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1009313API
curl https://kongchang.com/api/v1/knowledge/claims/1009313MCP
get_claim(id=1009313)