AIが動く。未来が更新される。Qwen3.8-9B-heretic-uncensored-4bit-MTPLX
Fast local build of rohit267/Qwen3.8-9B-heretic-uncensored for Apple Silicon, tuned for native-MTP speculative decoding with MTPLX. Measured **21.25 -> 40.05 decode tok/s (+88%)** on an M5 24GB MacBook, **lossless** (exact speculative verify - the emitted tokens match the target model's own decoding). The adapter is **merged at load time**; it is not baked into `mtp.safetensors`, so the base sidecar stays reusable.
翻訳準備中のため原文を表示しています
Fast local build of rohit267/Qwen3.8-9B-heretic-uncensored for Apple Silicon, tuned for native-MTP speculative decoding with MTPLX. Measured **21.25 -> 40.05 decode tok/s (+88%)** on an M5 24GB MacBook, **lossless** (exact speculative verify - the emitted tokens match the target model's own decoding). The adapter is **merged at load time**; it is not baked into `mtp.safetensors`, so the base sidecar stays reusable.