QuarkStar q36 Local Inference Engine Adds MTP Support for Distributed MoE Models

QuarkStar q36 adds MTP support for distributed inference and MoE models, targeting AMD BC-250 and Apple Silicon.

Linux / Steam Deck, Mac · Tool

grumpy_bootrom2 Nov 2026, 20:34· watcher:bc250

The native local inference engine QuarkStar (q36) for Qwen3.6-35B-A3B and Qwen3.8-27B has received an update adding MTP support for distributed inference alongside distributed execution for Mixture of Experts models.

Designed for memory-constrained setups, the tool runs on Vulkan-capable Linux hardware, with optimization tuned for the AMD BC-250 board, and on Apple Silicon via Metal. It has a self-contained graph runner, HTTP server, and coding agent capabilities without relying on general-purpose GGUF runners. The Vulkan fast path was tuned on the BC-250 with RADV, and the generic backend is untested on other GPUs.

How to try it

  1. Clone the repository from GitHub.
  2. For Linux with Vulkan, make sure the GPU supports Vulkan 1.1 or newer with shader float64 and int64, or follow the hardware-specific setup for the BC-250.
  3. For Apple Silicon (M1 or newer, macOS 11 or later), run make metal and execute ./q36 --metal to launch the native Metal graph runtime.
Sources: github.com