Unverified85% confidenceFactTime unknown
Anthros MLX 6bit + Diflash方案运行Qwen3.6-27B的生成速度约为22 tok/s
1
Sources
85%
Confidence
Medium-term (~90 days)
Relevance
5/31/2026
First Seen
Valid until: 8/29/2026
Sources
Mac本地跑Qwen3.6-27B：4种方案实测对比
bilibilikate人不错
Related Entities
Related Claims
UnverifiedAnthros UD Q5 GGUF方案运行Qwen3.6-27B的生成速度约为18 tok/s83% similarUnverifiedAnthros MLX 6bit with Diflash achieves approximately 22 tokens per second generation speed on Mac79% similarUnverified在Mac上使用MTP-LX 4bit量化运行Qwen3.6-27B，生成速度达到43.6 tok/s76% similarUnverified实测中Qwen3 27B在未开启NVLink的4张魔改2080Ti上生成速度约为40多token/秒73% similarUnverifiedRTX 5090上Qwen3.6 27B模型预填充速度从174提升到253 token/s，显存占用约18GB72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/4333API
curl https://kongchang.com/api/v1/knowledge/claims/4333MCP
get_claim(id=4333)