alt.freeweights.mimo / MiMo-V2.6-Flash-RL-GGUF

From:

ggml-org <huggingface.co/ggml-org>Newsgroups: alt.freeweights.mimoSubject:

MiMo-V2.6-Flash-RL-GGUF

Date: 2026-11-14Commit: de3ce28Signed: 2DC28CC7B26A283B ✓

Image text to text model. Gguf weights, 315 GB in all. Published by ggml-org under MIT.

mimo

315GBMiMo-V2.6-Flash-RL-GGUFggufpermissive

FactsParamsnot statedSize315 GBFormatsggufTaskimage text to textLicenseMITFrom sourcepermissive

$ fw get ggml-org/MiMo-V2.6-Flash-RL-GGUF
# manifest sha256 58623bc78192… · 315 GB · 15 files
$ fw verify ./MiMo-V2.6-Flash-RL-GGUF ggml-org/MiMo-V2.6-Flash-RL-GGUF

From sourceHosted (signed)ggml-org/MiMo-V2.6-Flash-RL-GGUFLast check: 2026-11-14 21:28 UTC

Run at home Get help

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Quantized of MiMo-V2.6-Flash-RL.

Works with

Run13 Convert1 Evaluate13 Scan12 Apps62

Runs with

Ranked by fit to this model (gguf), then by GitHub stars.

Text Generation WebUI mistral.rs

Ollama

llama.cpp LocalAI

BitNet llamafile KoboldCpp PocketPal AI llama-swap ik_llama.cpp RamaLama

Show all 13

Maid

Convert with

ggml

Evaluate with

Opik DeepEval Ragas lm-evaluation-harness OpenCompass SWE-bench

simple-evals TruLens HELM

LightEval

Evaluate Weave

Show all 13

Autoevals

Scan with

promptfoo garak Guardrails NeMo Guardrails Giskard DeepTeam AI Fairness 360 Fairlearn Detoxify MCP Scanner AgentDojo ModelScan

Overview Model card Files Use it License Provenance Model tree

Overview

Size: 315 GB
Weights: 1.26 GB (smallest of 7 GGUF variants)
Parameters: not stated
Formats: gguf
Task: image text to text
License: MIT (permissive)
Files: 15, each with a sha256
Publisher: ggml-org
Added: 2026-11-14
Section: alt.freeweights.mimo

Lineage

Original release from the publisher.

Base model: XiaomiMiMo/MiMo-V2.6-Flash-RL

Where these bytes come from

Publisher at the pinned commit→You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources

Badge	Host	Last check	Result
From source	huggingface.co	2026-11-14 21:28 UTC	passed

Model card

From the publisher at commit de3ce28. Shown as plain text with links; images open at the publisher.

MiMo-V2.6-Flash-RL#

Run it in the Llama app: https://llama.app

Or from the terminal:

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

Source models#

https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL

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

Files

15 files · 315 GBWeights 1.26 GB (smallest of 7 GGUF variants). Sizes and sha256 from the signed manifest.

Hide all 15 files with their sha256

File	Size	sha256
.gitattributes	2.41 KB	45b2b9beba56fd3d022669e788a0ff3068b24dd03c08768efaf23ff66822db96
.src_sha	49 B	c23ecd65c0df66ab7b2967936e9f949435279d423ea69ef798869eecb730bc8c
MiMo-V2.6-Flash-RL-MXFP4-00001-of-00002.gguf	5.95 MB	bfe6e56f0d5db768371a6f5133cadf480a7f45194ba5c2b7a6aa6f21e4813f5a
MiMo-V2.6-Flash-RL-MXFP4-00002-of-00002.gguf	167 GB	10b74ff85577de18b336718c19905a50bcbccfee9cae7b9edd446667084f623c
MiMo-V2.6-Flash-RL-Q2_K-00001-of-00002.gguf	5.95 MB	bfe6e56f0d5db768371a6f5133cadf480a7f45194ba5c2b7a6aa6f21e4813f5a
MiMo-V2.6-Flash-RL-Q2_K-00002-of-00002.gguf	126 GB	d037fe34f375e55945dbb981ae6bf4bd357cb19ee8c04f56fbd7c4dde4cdbd63
README.md	1.00 KB	1bc334cae562fb857403d58d6f95136ba4786d696c143ded25e68cbe28cec4f9
convert.log	483 KB	ec28278bfc5edd7ae5a0275caac3c60a169b5be6528aca18756cab6aab9a5a80
dflash-MiMo-V2.6-Flash-RL-BF16.gguf	5.44 GB	ca27cbe8a93c6fd63fa64fa7d3b8a795f62bf569b5795c70e70fcc3a022057f5
dflash-MiMo-V2.6-Flash-RL-Q8_0.gguf	2.89 GB	433982ebaaacc061adffd93a03e2a31027da0cad8a342a10901f4aec0ec6d29f
mmproj-MiMo-V2.6-Flash-RL-BF16.gguf	2.75 GB	1561e6127de6c1aa0d11b50c95205b65dbc6e4a4b8a6bf899cac1f7471fa0414
mmproj-MiMo-V2.6-Flash-RL-Q8_0.gguf	1.56 GB	9f3aeb85745e89d3f57af792f3d90704bdf8b4a2340ac5c2abb74ba6498490f4
mtp-MiMo-V2.6-Flash-RL-BF16.gguf	4.48 GB	dc8b5b07bb1de18b344bd51a09b73abcf172ff294c1731b6a990179d110d1735
mtp-MiMo-V2.6-Flash-RL-Q4_0.gguf	1.26 GB	33dc6c0df4b5dce97f8f4af1bd04e8d980733cfd1ec67e98fd7f364f64fc9dae
mtp-MiMo-V2.6-Flash-RL-Q8_0.gguf	2.38 GB	fe3343e67c7b6541139f511c9cd9ed167fcb942822a02984caccc0c57f90963a

VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.

Upstream commit	Date	Contents
de3ce28cec pinned now manifest updated, same commit	2026-11-14 21:28 UTC	15 files · 315 GB
de3ce28cec	2026-11-14 21:28 UTC	15 files · 315 GB

Use it

$ fw get ggml-org/MiMo-V2.6-Flash-RL-GGUF
# manifest sha256 58623bc78192… · 315 GB · 15 files
$ fw verify ./MiMo-V2.6-Flash-RL-GGUF ggml-org/MiMo-V2.6-Flash-RL-GGUF

fw.pyChecks the signature and every sha256, tries each source in order, resumes.

$ python3 fw.py get https://freeweights.allternit.com/manifests/ggml-org/MiMo-V2.6-Flash-RL-GGUF.json --dir ./MiMo-V2.6-Flash-RL-GGUF
$ python3 fw.py verify ./MiMo-V2.6-Flash-RL-GGUF ./ggml-org__MiMo-V2.6-Flash-RL-GGUF.json

hfThe Hugging Face CLI with one setting. Same repo id.

$ HF_ENDPOINT=https://freeweights.allternit.com hf download ggml-org/MiMo-V2.6-Flash-RL-GGUF --revision de3ce28cec5779ac9195eace412c049bf4d781cd --local-dir ./MiMo-V2.6-Flash-RL-GGUF

llama.cppDownload one GGUF variant (mtp-MiMo-V2.6-Flash-RL-Q4_0, 1.26 GB), then serve it.

$ HF_ENDPOINT=https://freeweights.allternit.com hf download ggml-org/MiMo-V2.6-Flash-RL-GGUF --include "mtp-MiMo-V2.6-Flash-RL-Q4_0*" --local-dir ./MiMo-V2.6-Flash-RL-GGUF
$ llama-server -m ./MiMo-V2.6-Flash-RL-GGUF/mtp-MiMo-V2.6-Flash-RL-Q4_0.gguf

OllamaMake an Ollama model from the downloaded file.

$ printf 'FROM ./MiMo-V2.6-Flash-RL-GGUF/mtp-MiMo-V2.6-Flash-RL-Q4_0.gguf\n' > Modelfile
$ ollama create mimo-v2.6-flash-rl-gguf -f Modelfile

Run at home

License

Name: MIT License
Id: MIT
Class: Permissive
Redistribution: yes
Listing: Hosted (signed)
Decided: License as declared by the publisher. No person read it. 2026-11-14
Text in: README.md
Text sha256: 1bc334cae562fb857403d58d6f95136ba4786d696c143ded25e68cbe28cec4f9
Terms gate: No extra terms beyond the license.

Read the license text

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From:

ggml-org <huggingface.co/ggml-org>Newsgroups: alt.freeweights.mimoSubject: MiMo-V2.6-Flash-RL-GGUFDate: 2026-11-14Commit: de3ce28Signed: 2DC28CC7B26A283B ✓

Upstream: ggml-org/MiMo-V2.6-Flash-RL-GGUF
Pinned commit: de3ce28cec5779ac9195eace412c049bf4d781cd
Manifest: MiMo-V2.6-Flash-RL-GGUF.json · .minisig
Manifest sha256: 58623bc781923754b588797c4b67bdef5d9fb0cfba1048ad8c182bd4f2dfa18b
Signature: minisign, Ed25519, key 2DC28CC7B26A283B
Created: 2026-11-14 21:28 UTC
Generator: freeweights-manifest/0.1.0
Takedowns: None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/ggml-org/MiMo-V2.6-Flash-RL-GGUF.json
$ curl -O https://freeweights.allternit.com/manifests/ggml-org/MiMo-V2.6-Flash-RL-GGUF.json.minisig
$ minisign -Vm MiMo-V2.6-Flash-RL-GGUF.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq
$ shasum -a 256 <file>   # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download