MiaAI-Lab/Qwen3.6-27B-NVFP4-vLLM

Self-hosted vLLM inference for Qwen3.6-35B-A3B-NVFP4

vLLM deployment for Unsloth Qwen3.6-35B-A3B-NVFP4-Fast on NVIDIA DGX Spark

vLLM Docker Container for the latest Qwen 27b

A custom inference engine tuned for Qwen4 architecture. Currently runs Qwen3.8-Flash-Next at 15+ tok/s on 16GB of VRAM and 30 GB of RAM

Deployment kit: Qwen3.8-27B EXL3 3.5bpw target + DFlash2 EXL3 5.0bpw speculative draft — launcher, config, model cards

All-NVFP4 vLLM + DFlash2 K7 for Blackwell (SM120/SM121): NVFP4 target/draft/KV, 262K context, optional CPU vision sidecar.

Qwen3.8-27B on 16-32 GB Nvidia GPUs one-click install for Windows / Linux

Quasar is an inference engine for Qwen3.6-27B-MTP / Qwen3.8-27B on consumer NVIDIA cards as well as Apple Silicon, in the spirit of antirez/ds4

Qwen3.8-27b and Qwen3.6-35B-A3B local inference engine for Vulkan and Metal