cff-version: 1.2.0
title: "Janus-35B: A Mixture-of-Experts Distillation Wrapper for Qwen 3.6 35B-A3B"
message: "If you use this model card or its accompanying files, please cite as below."
type: software
authors:
  - name: FoolDev
    website: "https://huggingface.co/FoolDev"
repository-code: "https://huggingface.co/FoolDev/janus"
url: "https://huggingface.co/FoolDev/janus"
abstract: >-
  Janus-35B is a personal repackaging of the Qwen 3.6 35B-A3B
  mixture-of-experts base model (35B total / 3B active per token,
  256 experts, 8 activated) with Claude Opus 4.7 in the reasoning
  teacher slot. The repository ships an Ollama Modelfile, the HF
  Ollama-bridge files (template / system / params), sampling defaults,
  and a bundled Q4_K_M GGUF (~19 GB) so the HF "Use this model" widget
  surfaces a one-liner Ollama snippet. Other quants and the upstream
  safetensors (Qwen/Qwen3.6-35B-A3B) are pulled from upstream on demand
  rather than redistributed.
keywords:
  - qwen
  - qwen3.6
  - mixture-of-experts
  - moe
  - distillation
  - reasoning
  - llm
license: Apache-2.0
references:
  - type: software
    title: "Qwen3.6-35B-A3B"
    authors:
      - name: Alibaba Qwen Team
    url: "https://huggingface.co/Qwen/Qwen3.6-35B-A3B"
  - type: software
    title: "Janus-27B (dense sibling)"
    authors:
      - name: FoolDev
    url: "https://huggingface.co/FoolDev/janus-27b"