待验证50% 置信事实时间未知
Anthros MLX 6bit with Diflash achieves approximately 22 tokens per second generation speed on Mac
1
来源数
50%
置信度
中期 (~90 天)
时效性
2026/7/2
首次发现
有效期至:2026/9/30
来源
Running Qwen3.6-27B Locally on Mac: 4 Solutions Benchmarked
bilibilikate人不错
相关事实
待验证MTP-LX with 4bit quantization achieves 40+ tokens per second generation speed on Mac, approximately double the speed of the MLX 6bit solution81% 相似待验证Anthros MLX 6bit + Diflash方案运行Qwen3.6-27B的生成速度约为22 tok/s79% 相似待验证Anthros UD Q5 GGUF quantization achieves approximately 18 tokens per second generation speed on Mac77% 相似待验证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73% 相似待验证27B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% 相似
引用此条事实
Stable URI
https://kongchang.com/claim/55307API
curl https://kongchang.com/api/v1/knowledge/claims/55307MCP
get_claim(id=55307)