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

MiMo-V2.6-Pro-MOPD-GGUF

Date: 2026-11-15Commit: cd70ac1Signed: 2DC28CC7B26A283B ✓

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

mimo1.01TBMiMo-V2.6-Pro-MOPD-GGUFggufpermissive
FactsParamsnot statedSize1.01 TBFormatsggufTaskimage text to textLicenseMITFrom sourcepermissive
$ fw get ggml-org/MiMo-V2.6-Pro-MOPD-GGUF
# manifest sha256 388a753e61f3… · 1.01 TB · 25 files
$ fw verify ./MiMo-V2.6-Pro-MOPD-GGUF ggml-org/MiMo-V2.6-Pro-MOPD-GGUF
From sourceHosted (signed)ggml-org/MiMo-V2.6-Pro-MOPD-GGUFLast check: 2026-11-15 05:02 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-MOPD.

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-MOPD

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 05:02 UTCpassed

Model card

From the publisher at commit cd70ac1. Shown as plain text with links; images open at the publisher.

MiMo-V2.6-Pro-MOPD#

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

Or from the terminal:

llama serve -hf ggml-org/MiMo-V2.6-Pro-MOPD-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.
  • The Q2_K expert gate/up tensors are calibrated with the imatrix from https://huggingface.co/AesSedai/MiMo-V2.6-Pro-MOPD-GGUF

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
.gitattributes3.14 KB17c15c7566fb9e16ca9dc3d8b465e6c739262d77a63ecba45ea18855b0f3663c
.src_sha49 B4c5e137af7f8b86afd9721977737beeceb1ae935bd177192ba2468a2e6ae0b5d
MiMo-V2.6-Pro-MOPD-MXFP4-00001-of-00007.gguf5.95 MBb30d0241359fcc5f9c18e71c8ba61448c3b64aa773dfd32c61f7e60244d6b1e0
MiMo-V2.6-Pro-MOPD-MXFP4-00002-of-00007.gguf97.5 GB7b42556e99b2e004fdd0070d4a502233c40443c65e67616b86d97642959f4064
MiMo-V2.6-Pro-MOPD-MXFP4-00003-of-00007.gguf97.5 GB6e9bb24d2d54985f3407b3065ac657cf5879f8cdc3243d69006c0f9e78b11265
MiMo-V2.6-Pro-MOPD-MXFP4-00004-of-00007.gguf97.5 GB576a9006b465da6bcf039b36849f52e40fdbb276085c96312baddc12debbcac6
MiMo-V2.6-Pro-MOPD-MXFP4-00005-of-00007.gguf97.5 GB2a66209f60116941d472c40a804526dc87687689aed7c20477c1eba023ff76ad
MiMo-V2.6-Pro-MOPD-MXFP4-00006-of-00007.gguf97.5 GBdff225984f20120b6de2c671bc2c8e5bbae7606177fae7e66b8d3b9a43ef68cb
MiMo-V2.6-Pro-MOPD-MXFP4-00007-of-00007.gguf66.5 GB1404524ae46f258300ad75c3638acb78bb626f7805af987997d53e27e0bc3805
MiMo-V2.6-Pro-MOPD-Q2_K-00001-of-00007.gguf5.95 MBb87221a1764b3c848af9e1c480eeba9c7181459ae2860e2b89f41ca3d7be6335
MiMo-V2.6-Pro-MOPD-Q2_K-00002-of-00007.gguf73.0 GBf8c44670392bd9e2699bd7ef04c1e87e2ff2cd9e3d4acbb05466ef908d8c0ff2
MiMo-V2.6-Pro-MOPD-Q2_K-00003-of-00007.gguf73.0 GBfd0d507dbb691eafb3717c85f98bd98d3e631c5eaa6cf0e7255d81604df00cd5
MiMo-V2.6-Pro-MOPD-Q2_K-00004-of-00007.gguf72.0 GBcd1074c5ae33ee9a25ef14317c971547bf0bf50b5fc05df6648bc118d022a8ca
MiMo-V2.6-Pro-MOPD-Q2_K-00005-of-00007.gguf73.0 GBc78ae07e1eecc78eee2b8016053ec53521b6009a2cd1b2671cece066004e2d97
MiMo-V2.6-Pro-MOPD-Q2_K-00006-of-00007.gguf73.0 GB6ac111255bd9b79ccef2c34ca4a8b975e191ed6f7eb45207680f9d27a8890ba1
MiMo-V2.6-Pro-MOPD-Q2_K-00007-of-00007.gguf54.7 GBcc09a29e090cfd36164c3a30f9c58700dac80f9c5e56801df9bf1580de9a50b9
README.md1.05 KB6b2706be5543519da523a5b6e2edbf824e6811097f7cb82b38f50508393a2930
convert.log630 KB451c6a34be31937b3777d5d9e8632571c35b4c514b925cbaa13f182026d09f84
dflash-MiMo-V2.6-Pro-MOPD-BF16.gguf9.29 GBfb9f08f513511aafca31e1f1ab1fa492c5926590a191026561583953c1d73938
dflash-MiMo-V2.6-Pro-MOPD-Q8_0.gguf4.94 GBb97e219318ec8b4e9792c5a3cfc211e2257ab6eb63ea355c67184e4d4e3183ec
mmproj-MiMo-V2.6-Pro-MOPD-BF16.gguf2.84 GBaaf5ff2f825cb8c5b37cc03777efb026deb212a3164711426692f5eff7f4a2af
mmproj-MiMo-V2.6-Pro-MOPD-Q8_0.gguf1.61 GB61ab5fa64b9d56fc5a0d5e9b565e42bfa922fe781c37c0d9618d5a6bca07e727
mtp-MiMo-V2.6-Pro-MOPD-BF16.gguf7.63 GBbc8e649446f0b20a9dd78817eac8b8941b72b16e10261d3125c6f8ab5510e474
mtp-MiMo-V2.6-Pro-MOPD-Q4_0.gguf2.15 GB79266332d5094fd758e6df3805f4758633a38b7bf53b8f7cf26262f0f71ec291
mtp-MiMo-V2.6-Pro-MOPD-Q8_0.gguf4.05 GB1403612d2265d7d8384aa01cbb63f6827f936a849f99e49be34d3d40a431c16f
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
cd70ac158e pinned now2026-11-15 05:02 UTC25 files · 1.01 TB

Use it

$ fw get ggml-org/MiMo-V2.6-Pro-MOPD-GGUF
# manifest sha256 388a753e61f3… · 1.01 TB · 25 files
$ fw verify ./MiMo-V2.6-Pro-MOPD-GGUF ggml-org/MiMo-V2.6-Pro-MOPD-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-MOPD-GGUF.json --dir ./MiMo-V2.6-Pro-MOPD-GGUF $ python3 fw.py verify ./MiMo-V2.6-Pro-MOPD-GGUF ./ggml-org__MiMo-V2.6-Pro-MOPD-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-MOPD-GGUF --revision cd70ac158ea81ca857eb0e6feb9fb46d4996a242 --local-dir ./MiMo-V2.6-Pro-MOPD-GGUF
llama.cppDownload one GGUF variant (mtp-MiMo-V2.6-Pro-MOPD-Q4_0, 2.15 GB), then serve it.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download ggml-org/MiMo-V2.6-Pro-MOPD-GGUF --include "mtp-MiMo-V2.6-Pro-MOPD-Q4_0*" --local-dir ./MiMo-V2.6-Pro-MOPD-GGUF $ llama-server -m ./MiMo-V2.6-Pro-MOPD-GGUF/mtp-MiMo-V2.6-Pro-MOPD-Q4_0.gguf
OllamaMake an Ollama model from the downloaded file.
$ printf 'FROM ./MiMo-V2.6-Pro-MOPD-GGUF/mtp-MiMo-V2.6-Pro-MOPD-Q4_0.gguf\n' > Modelfile $ ollama create mimo-v2.6-pro-mopd-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
6b2706be5543519da523a5b6e2edbf824e6811097f7cb82b38f50508393a2930
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-MOPD-GGUFDate: 2026-11-15Commit: cd70ac1Signed: 2DC28CC7B26A283B ✓
Upstream
ggml-org/MiMo-V2.6-Pro-MOPD-GGUF
Pinned commit
cd70ac158ea81ca857eb0e6feb9fb46d4996a242
Manifest
MiMo-V2.6-Pro-MOPD-GGUF.json · .minisig
Manifest sha256
388a753e61f36c8b7c099d9b8afa57139d96a0795b1ac22397fd36d48448e813
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:02 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-MOPD-GGUF.json $ curl -O https://freeweights.allternit.com/manifests/ggml-org/MiMo-V2.6-Pro-MOPD-GGUF.json.minisig $ minisign -Vm MiMo-V2.6-Pro-MOPD-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-MOPD · 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-MOPD-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-MOPD-GGUF.json. Provenance. Takedown history: none.
Source
huggingface.co/ggml-org/MiMo-V2.6-Pro-MOPD-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