🧰 Docker Model Runner

The items that name it 8

• DeepSeek-v4.1-Flash-1017
  repo2026-10-17

  Runs the model locally with docker model run hf.co/deepseek-ai/DeepSeek-V4.1-Flash-1017

• Meta Muse Spark Open (816B-A42B) open-weights model card
  repo

  Run the model locally with docker model run hf.co/meta-models/Muse-Spark-Open-816B-A42B

• Qwen3.8-27B (Apache-2.0, multimodal dense, 262k ctx)
  repo

  Run the model via docker model run hf.co/Qwen/Qwen3.8-27B

• Tencent Hy4 preview (open-weight MoE + Sherry quantization)
  repo

  Runs tencent/Hy4-preview directly from a Docker command (docker model run hf.co/tencent/Hy4-preview)

• DeepSeek-V4.1-Flash
  repo

  Runs DeepSeek-V4.1-Flash directly via 'docker model run hf.co/deepseek-ai/DeepSeek-V4.1-Flash'

• Ternary-Bonsai-2-27B: 27B model compressed to ~1.75 bits/weight, 98.2% of FP16 quality retained
  repo

  Docker-based tool to run the model directly from a Hugging Face reference

• MiMo-V2.6-Pro-RL
  repo

  Run MiMo-V2.6-Pro-RL locally via 'docker model run hf.co/...'

• MiMo-V2.6-Flash-RL (Xiaomi)
  repo

  Runs MiMo-V2.6-Flash-RL directly from a Hugging Face reference via Docker

In every workspace you can read 10