AI가 움직이고 미래가 업데이트됩니다.Ternary-Bonsai-2-27B-MTPLX-Optimized-Speed
**MTPLX: the fastest way to run Ternary Bonsai 2 27B on a Mac. Native multi-token-prediction speculative decoding on Apple Silicon, exact at any temperature.** Prism ML's Ternary Bonsai 2 27B is Qwen 3.8 27B rebuilt with ternary weights, and Prism ML reports it keeps 98.2 percent of the full model's benchmark average in 8.85 GB. On MTPLX it runs on GPU kernels written for it, with the Qwen 3.8 27B multi-token-prediction head drafting ahead. That makes it faster than the 4-bit Qwen 3.8 27B in half the memory. It reads images, and it runs on a Mac with 16 GB. Prism ML's own figure for Bonsai 2 27B on an M5 Max with MLX is 46.8 tok/s. On MTPLX the same chip decodes it at 64.4 tok/s after a 4,061-token prompt.
번역 준비 중입니다. 원문을 표시합니다.
**MTPLX: the fastest way to run Ternary Bonsai 2 27B on a Mac. Native multi-token-prediction speculative decoding on Apple Silicon, exact at any temperature.** Prism ML's Ternary Bonsai 2 27B is Qwen 3.8 27B rebuilt with ternary weights, and Prism ML reports it keeps 98.2 percent of the full model's benchmark average in 8.85 GB. On MTPLX it runs on GPU kernels written for it, with the Qwen 3.8 27B multi-token-prediction head drafting ahead. That makes it faster than the 4-bit Qwen 3.8 27B in half the memory. It reads images, and it runs on a Mac with 16 GB. Prism ML's own figure for Bonsai 2 27B on an M5 Max with MLX is 46.8 tok/s. On MTPLX the same chip decodes it at 64.4 tok/s after a 4,061-token prompt.