Unverified60% confidenceBenchmarkExact time
Ornith 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
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
Unverified在16GB Mac Mini上Ornith 9B简单请求下生成速度约为16 tokens/秒83% similarUnverifiedMTP-LX with 4bit quantization achieves 40+ tokens per second generation speed on Mac, approximately double the speed of the MLX 6bit solution77% similarUnverifiedAnthros MLX 6bit with Diflash achieves approximately 22 tokens per second generation speed on Mac73% 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/s72% 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tokens71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/176266API
curl https://kongchang.com/api/v1/knowledge/claims/176266MCP
get_claim(id=176266)