model: MiMo-V2.6-Flash-RL (mimo2, 309B/15B)

Closed
#61 1 comment 0 reactions 0 assignees View on GitHub

Maintainers usually reply within 1 day

Nobody has claimed this yet.

Assessment

Difficulty
5/5
Estimated time
Over a week
Newbie friendliness
25/100
Issue type
Feature
Clarity
Needs clarification
Activity status
Active
Tech stack
rust

Research direction

Start by comparing the linked Hugging Face config and GGUF files with the existing mimo2 seat implementation and its model loading tests. Check whether the RL file loads with the existing MXFP4 layout and refset identity, then determine whether the separate MTP file needs support. Done means documenting or implementing the required compatibility changes and verifying the model loads; the issue names no source files or tests.

Written by the indexing model from the issue text.

Description

model

Xiaomi's RL-tuned MiMo-V2.6-Flash, the same family as our mimo2 seat.

GGUF: https://huggingface.co/ggml-org/MiMo-V2.6-Flash-RL-GGUF (arch mimo2; MXFP4 167 GB, Q2_K 126 GB [derived: shard sum]; separate mtp- and dflash- files).

Reuses: the whole mimo2 seat. Expected new code: none [derived from equal configs].

Open questions:

  • Does the RL file load unchanged (MXFP4 layout, refset identity)?
  • Does the separate MTP file matter? The seat has no MiMo draft today.

Surveyed with an AI agent; facts link their sources.

Dominant language
Rust
Stars
21
Forks
4
Avg merge
2h 32m
Merged PRs (30d)
803

Getting set up

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from midagedev/bloomery

All issues in midagedev/bloomery

Similar issues

More Rust issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.