CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.mimo / MiMo-V2.6-Pro-RL-GGUF
From: ggml-org <huggingface.co/ggml-org>Newsgroups: alt.freeweights.mimoSubject:

MiMo-V2.6-Pro-RL-GGUF

Date: 2026-11-15Commit: 5f387f5Signed: 2DC28CC7B26A283B ✓

Image text to text model. Gguf weights, 1.01 TB in all. Published by ggml-org under MIT.

mimo1.01TBMiMo-V2.6-Pro-RL-GGUFggufpermissive
FactsParamsnot statedSize1.01 TBFormatsggufTaskimage text to textLicenseMITFrom sourcepermissive
$ fw get ggml-org/MiMo-V2.6-Pro-RL-GGUF
# manifest sha256 3bd230dc8a66… · 1.01 TB · 25 files
$ fw verify ./MiMo-V2.6-Pro-RL-GGUF ggml-org/MiMo-V2.6-Pro-RL-GGUF
From sourceHosted (signed)ggml-org/MiMo-V2.6-Pro-RL-GGUFLast check: 2026-11-15 04:57 UTC
Run at homeGet help

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

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

Works with

Run13Convert1Evaluate13Scan12Apps62

Convert with

ggml
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

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

Original release from the publisher.

Base model: XiaomiMiMo/MiMo-V2.6-Pro-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
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-15 04:57 UTCpassed

Model card

From the publisher at commit 5f387f5. Shown as plain text with links; images open at the publisher.

MiMo-V2.6-Pro-RL#

Run with https://llama.app

llama serve -hf ggml-org/MiMo-V2.6-Pro-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

Files

25 files · 1.01 TBWeights 2.15 GB (smallest of 7 GGUF variants). Sizes and sha256 from the signed manifest.
Show all 25 files with their sha256
FileSizesha256
.gitattributes3.10 KBe81040f8319851bebbf1bee873cd60f229f970b4889ffd6323ef47da7010f40c
.src_sha49 Bad11e2abb55bd38e349ad760a41e6d317a5e461218b6bbdd116d236c32fc96a5
MiMo-V2.6-Pro-RL-MXFP4-00001-of-00007.gguf5.95 MB4d77de566b7bc5c283b1a5b8b0b73bdfd539d939f72d2a82e231e90323fd1589
MiMo-V2.6-Pro-RL-MXFP4-00002-of-00007.gguf97.5 GB85973b1eb0b0bb54a6d7acccf412356b644dad472434557f4460fd1c2ae7c798
MiMo-V2.6-Pro-RL-MXFP4-00003-of-00007.gguf97.5 GB11f22ddfafd936643f208977aa17ed009d48f913aea9e3d47846482b8a4bdf4c
MiMo-V2.6-Pro-RL-MXFP4-00004-of-00007.gguf97.5 GBc8ea6e7ea7655f43a3454aaca5d3b22d12f20b4afb48fc468d8c624162de0bf2
MiMo-V2.6-Pro-RL-MXFP4-00005-of-00007.gguf97.5 GB74becd913d58917e19bd3005759d59708845e42ec499a01e82db500ecfe0db56
MiMo-V2.6-Pro-RL-MXFP4-00006-of-00007.gguf97.5 GBd7183ce566d19264f4e1310155f7f9ffc8702906b2ee0b418a81736e67b2c77e
MiMo-V2.6-Pro-RL-MXFP4-00007-of-00007.gguf66.5 GBc1219a9dfed8b754146890eb7b818fe86b325ffd5ef1324b7d1e01cdc9627a0f
MiMo-V2.6-Pro-RL-Q2_K-00001-of-00007.gguf5.95 MB4d77de566b7bc5c283b1a5b8b0b73bdfd539d939f72d2a82e231e90323fd1589
MiMo-V2.6-Pro-RL-Q2_K-00002-of-00007.gguf73.0 GBb81b64562d789fe88c3d42c4072e3cdff8745d7bd07cac2ef5cc4e1bf702cd10
MiMo-V2.6-Pro-RL-Q2_K-00003-of-00007.gguf73.0 GBc04d259a8e39fb218b44c84a2eda56683e42b57d3526a33a37ad05d8533305c4
MiMo-V2.6-Pro-RL-Q2_K-00004-of-00007.gguf72.0 GBb87672f0d7b6837cc9aa570509bad1df04297e78fc6f9a3ed952e5995370d757
MiMo-V2.6-Pro-RL-Q2_K-00005-of-00007.gguf73.0 GB96a80f8a84115676bb8cfcddb269c4c707bbe48f80285cdcaed66b059eab2444
MiMo-V2.6-Pro-RL-Q2_K-00006-of-00007.gguf73.0 GB96545052070a0608dd349be7c6323675b56a9c8dabcb627de9ddb42bd32f18a7
MiMo-V2.6-Pro-RL-Q2_K-00007-of-00007.gguf54.7 GB8e26e78b61e541f32e4a0e546c228954cb0cb95951368f14ccbf94aac3de5130
README.md953 B3c0dac0ff3ed5d634c4b6630439ba3e22c67d7cac0fb5b4accd0e5c96ed152c0
convert.log616 KB33a5bb99b22037d061e53d2ed55f4dbc1304cd301378b38fb6d41a9255df254c
dflash-MiMo-V2.6-Pro-RL-BF16.gguf9.29 GB05a38292e45c4684c02875e111a27c02d39ebd3e11aea12fb303dbd10bd754dd
dflash-MiMo-V2.6-Pro-RL-Q8_0.gguf4.94 GB50260b30115a268a66a463d5628fb3c0762765e69e59d473458527ea5cb90db2
mmproj-MiMo-V2.6-Pro-RL-BF16.gguf2.84 GB9acca6b1eadadf557232f1a6a742f8fe08235e594b8f8e9f6068f89e85038c8e
mmproj-MiMo-V2.6-Pro-RL-Q8_0.gguf1.61 GBc82b726922800eb670857f454b463ccd919a4202cec13e01dfb34e1774f483a6
mtp-MiMo-V2.6-Pro-RL-BF16.gguf7.63 GB0ac5700ccb15d1b2f8004f846b1533448e5bf20c9770371d3d2a26003a73be2b
mtp-MiMo-V2.6-Pro-RL-Q4_0.gguf2.15 GB741be72c45a9b9c1265f746baf4f124da3d37a4378f262782c732578e55021c1
mtp-MiMo-V2.6-Pro-RL-Q8_0.gguf4.05 GBbc342d88400dccf3c830feba538630816cb5594bcfe36c6fef8561c81a1ef37f
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
5f387f5260 pinned now2026-11-15 04:57 UTC25 files · 1.01 TB

Use it

$ fw get ggml-org/MiMo-V2.6-Pro-RL-GGUF
# manifest sha256 3bd230dc8a66… · 1.01 TB · 25 files
$ fw verify ./MiMo-V2.6-Pro-RL-GGUF ggml-org/MiMo-V2.6-Pro-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-Pro-RL-GGUF.json --dir ./MiMo-V2.6-Pro-RL-GGUF $ python3 fw.py verify ./MiMo-V2.6-Pro-RL-GGUF ./ggml-org__MiMo-V2.6-Pro-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-Pro-RL-GGUF --revision 5f387f5260fc110678396a3076a140c469b41eaa --local-dir ./MiMo-V2.6-Pro-RL-GGUF
llama.cppDownload one GGUF variant (mtp-MiMo-V2.6-Pro-RL-Q4_0, 2.15 GB), then serve it.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download ggml-org/MiMo-V2.6-Pro-RL-GGUF --include "mtp-MiMo-V2.6-Pro-RL-Q4_0*" --local-dir ./MiMo-V2.6-Pro-RL-GGUF $ llama-server -m ./MiMo-V2.6-Pro-RL-GGUF/mtp-MiMo-V2.6-Pro-RL-Q4_0.gguf
OllamaMake an Ollama model from the downloaded file.
$ printf 'FROM ./MiMo-V2.6-Pro-RL-GGUF/mtp-MiMo-V2.6-Pro-RL-Q4_0.gguf\n' > Modelfile $ ollama create mimo-v2.6-pro-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. 2026-11-15
Text in
README.md
Text sha256
3c0dac0ff3ed5d634c4b6630439ba3e22c67d7cac0fb5b4accd0e5c96ed152c0
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-Pro-RL-GGUFDate: 2026-11-15Commit: 5f387f5Signed: 2DC28CC7B26A283B ✓
Upstream
ggml-org/MiMo-V2.6-Pro-RL-GGUF
Pinned commit
5f387f5260fc110678396a3076a140c469b41eaa
Manifest
MiMo-V2.6-Pro-RL-GGUF.json · .minisig
Manifest sha256
3bd230dc8a66cb8d1a0cd81e0182cb4c6c67fdbfa98ea78d1bbed35bf29037d4
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 04:57 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/ggml-org/MiMo-V2.6-Pro-RL-GGUF.json $ curl -O https://freeweights.allternit.com/manifests/ggml-org/MiMo-V2.6-Pro-RL-GGUF.json.minisig $ minisign -Vm MiMo-V2.6-Pro-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

Model tree

Parent

XiaomiMiMo/MiMo-V2.6-Pro-RL · this model is a quantization of it

No model in the catalog names this one as its parent.

Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download ggml-org/MiMo-V2.6-Pro-RL-GGUF
Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest
minisign, key 2DC28CC7B26A283B. MiMo-V2.6-Pro-RL-GGUF.json. Provenance. Takedown history: none.
Source
huggingface.co/ggml-org/MiMo-V2.6-Pro-RL-GGUF

Related models

All of alt.freeweights.mimo →
From: XiaomiMiMo <huggingface.co/XiaomiMiMo>Subject: MiMo-7B-Base
From: XiaomiMiMo <huggingface.co/XiaomiMiMo>Subject: MiMo-V2-Flash
From: unsloth <huggingface.co/unsloth>Subject: MiMo-V2-Flash-GGUF
From: XiaomiMiMo <huggingface.co/XiaomiMiMo>Subject: MiMo-V2.5
From: XiaomiMiMo <huggingface.co/XiaomiMiMo>Subject: MiMo-V2.5-ASR
From: mlx-community <huggingface.co/mlx-community>Subject: MiMo-V2.5-ASR-MLX-8bit