MiaAI-Lab/Qwen3.6-35B-A3B-NVFP4-vLLM

Production-ready vLLM deployment wrapper for Qwen3.6-27B (NVFP4) — self-hosted OpenAI-compatible inference

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

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

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

High-performance single-GPU inference for selected model checkpoints and GPUs.

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

Self-hosted, OpenAI-compatible inference for the agentic era: reasoning LLMs, universal tool calling, and the Responses API alongside embeddings, speech, and image models — many models sharing your GPUs, one gateway. Powered by Ray Serve.

vLLM Docker Container for the latest Qwen 27b

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