Unverified60% confidenceBenchmarkExact time
在16GB Mac Mini上Ornith 9B简单请求下生成速度约为16 tokens/秒
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
7/7/2026
First Seen
Valid until: 10/5/2026
Sources
Ornith 9B实测:16GB Mac Mini能否胜任本地AI编码?
bilibili四月的尾巴_7/4/2026
Related Claims
UnverifiedOrnith 35B(4bit MLX)在Mac Studio上生成速度约100 tokens/秒,比9B在Mac Mini上快近5倍83% 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% similarUnverified在16GB M4 Mac Mini上,Ornith 9B GGUF版本加载后6.2GB用于模型权重,最大上下文长度可达26万tokens70% 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69% similarUnverifiedGemma量化模型在高性能笔记本电脑上Token生成速度可达每秒20-50个,纯CPU推理约5-15 tokens/秒,INT4量化下NVIDIA RTX 4060/4070可将推理速度提升3-5倍67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/176265API
curl https://kongchang.com/api/v1/knowledge/claims/176265MCP
get_claim(id=176265)