Rapid-MLX 0.16.7：Mac 上 V4.1 Flash 解码提速约 2 倍

Rapid-MLX · local AI on your Mac @rapidmlx原推发布于 2026.10.22

在 X 上打开原推

Rapid-MLX 0.16.7 is out: DeepSeek V4.1 Flash runs up to ~2x faster on a Mac. Our quant of DeepSeek-V4.1-Flash-1017 (GPTQ v2) now decodes at 33–45 tok/s single-stream on an M3 Ultra. Same weights, faster engine: lighter drafting, fused mixed-bit MoE, and a vocab head read once per verify round. Every token is still verified by the full model. pip install -U rapid-mlx rapid-mlx serve deepseek-v41-flash-1017 Try it out: https://rapidmlx.com/download

这条是引用着另一条写的：「rapid-mlx 发布 V4.1 Flash MLX 量化：256GB Mac 可跑，top-1 85.1%」