Inco Splash open-source engine hits 144 tok/s on Qwen3.8-27B in an M5 Max
Lianhuiq · x · 2026-09-19
Inco released Inco Splash, an open-source inference engine built around the model and Apple silicon: Qwen3.8-27B runs at 144 tok/s on an M5 Max MacBook Pro. Claimed decode speed is up to 3x Ollama, 2x oMLX, and nearly 4x when an agent fans out into sub-agents.
More from Infra
- S3-based databases cache in memory and NVMe, making disk vs S3 latency gap smaller than expected — mgill25 · 2026-11-04
- gpu-unlock project claims up to 2x FP16 tensor throughput for RTX 20/30/40 cards — paranoidray · 2026-11-04
- These 10 GPU optimization papers are why your model runs fast today — NandoDF · 2026-11-04
- One prompt to audit cross-region traffic: dev cut trans-Atlantic latency by moving a service — DanielLockyer · 2026-11-04
- SurrealDB 4 launches as multi-model ACID database for the agentic era — Scobleizer · 2026-11-04
- Fire at Taiwan Panasonic PCB materials plant may tighten CCL supply further — zephyr_z9 · 2026-11-04