Qwen3.6-35B-A3B (NVFP4 (compressed-tensors))

Alibaba / Qwen · Qwen3.6
LLMApache-2.0publicTrusted35B params

Ready-made NVFP4 (compressed-tensors) build - runs on the fleet stack (compressed-tensors). Blackwell window.

Ready-made NVFP4 (compressed-tensors) build - runs on the fleet stack (compressed-tensors). Blackwell window.

At a glance

  • Task: LLM (InferenceV1)
  • Params: 35B
  • License: Apache-2.0 (commercial use OK)
  • Hardware: 28 GB+ VRAM
  • dtype: Nvfp4