deepseek-v4.1POST
Rapid-MLX 0.16.7: DeepSeek V4.1 Flash decodes ~2x faster on Mac
Rapid-MLX 0.16.7 speeds up its GPTQ v2 quant of DeepSeek-V4.1-Flash-1017 to 33–45 tok/s single-stream on an M3 Ultra via lighter drafting, fused mixed-bit MoE and a once-per-verify vocab head.
Rapid-MLX · local AI on your Mac
@rapidmlxArchived 10 days agoOriginally posted 2026.10.22
Rapid-MLX · local AI on your Mac @rapidmlxOriginally posted 2026.10.22
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
This post quotes another post: “rapid-mlx ships DeepSeek V4.1 Flash MLX quant for 256GB+ Macs”
x.com/rapidmlx/status/2113095409623245208Archived 2026.10.22 11:58