中文Sign up

ggml-org/MiMo-V2.6-Flash-RL-GGUF

🤗 Hugging Face sourceimage-text-to-textmit582 GBGGUF✓ 11 checksumsupdated today
Submit in one command

Run it next to your model folder. It makes the torrent, checks your files against Hugging Face, and submits it. You just start seeding and paste your key from your account. It only reads your files and never changes them. Read the script first if you like.

curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo ggml-org/MiMo-V2.6-Flash-RL-GGUF ./model-folder
Needs a seeder →

MiMo-V2.6-Flash-RL

Run with https://llama.app

llama serve -hf ggml-org/MiMo-V2.6-Flash-RL-GGUF

Source models

Notes

  • The MXFP4 output keeps the routed experts at their native MXFP4 precision.
  • The Q2_K output keeps the expert down projections at MXFP4, and quantizes the gate/up projections to Q2_K.
  • Includes MTP sidecars (Q4_0 and Q8_0) for speculative decoding (--mtp).
  • Includes a DFlash drafter sidecar (BF16 and Q8_0) for speculative decoding, converted from the dflash/ subdirectory of the source repo.
  • Includes a Q8_0 mmproj for the vision and audio encoders.
  • Currently, the Q2 models do not use an imatrix calibration due to lack of one.

[!IMPORTANT] This model is automatically converted using https://github.com/ggml-org/convert