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

MiMo-V2.6-Flash-MOPD-GGUF

Date: 2026-11-15Commit: c9d8697Signed: 2DC28CC7B26A283B ✓

Image text to text model. Gguf weights, 420 GB in all. Published by ggml-org under MIT.

mimo420GBMiMo-V2.6-Flash-MOPD-GGUFggufpermissive
FactsParamsnot statedSize420 GBFormatsggufTaskimage text to textLicenseMITFrom sourcepermissive
$ fw get ggml-org/MiMo-V2.6-Flash-MOPD-GGUF
# manifest sha256 2d989404e103… · 420 GB · 17 files
$ fw verify ./MiMo-V2.6-Flash-MOPD-GGUF ggml-org/MiMo-V2.6-Flash-MOPD-GGUF
From sourceHosted (signed)ggml-org/MiMo-V2.6-Flash-MOPD-GGUFLast check: 2026-11-15 04:50 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-Flash-MOPD.

Works with

Run13Convert1Evaluate13Scan12Apps62

Convert with

ggml
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
420 GB
Weights
1.26 GB (smallest of 8 GGUF variants)
Parameters
not stated
Formats
gguf
Task
image text to text
License
MIT (permissive)
Files
17, 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-Flash-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 04:50 UTCpassed

Model card

From the publisher at commit c9d8697. Shown as plain text with links; images open at the publisher.

MiMo-V2.6-Flash-MOPD#

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

Or from the terminal:

llama serve -hf ggml-org/MiMo-V2.6-Flash-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.
  • The Q2_K_S output is smaller than Q2_K - all routed expert projections (down, gate, up) are quantized 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 / Q2_K_S expert tensors are calibrated with the imatrix from https://huggingface.co/AesSedai/MiMo-V2.6-Flash-MOPD-GGUF

Important. This model is automatically converted using https://github.com/ggml-org/convert

Files

17 files · 420 GBWeights 1.26 GB (smallest of 8 GGUF variants). Sizes and sha256 from the signed manifest.
Hide all 17 files with their sha256
FileSizesha256
.gitattributes2.53 KBf7ba55c6c309967d3c0be472a50f4a584bf159b6eb306c70f13a65efe50094ca
.src_sha49 Bd56a9754515895b7487c5e4e8058859467b5caf9d5a4c8ba127e5b5f4cddad21
MiMo-V2.6-Flash-MOPD-MXFP4-00001-of-00002.gguf5.95 MBb1cb983931f3b90771a2db88470db49a5294a188de66c8852513e9d8a73894c9
MiMo-V2.6-Flash-MOPD-MXFP4-00002-of-00002.gguf167 GB3adf8ea80157dd066945a954428ba0e507c15c0e5a8b6b276ac92df0948698bc
MiMo-V2.6-Flash-MOPD-Q2_K-00001-of-00002.gguf5.95 MB3833ef22d82c9ca168392b620c5f1b919855e656955e3b01473819260c65bda3
MiMo-V2.6-Flash-MOPD-Q2_K-00002-of-00002.gguf126 GB637921c1b5b556f422c548c2b2ff96384baaeb86a86c2081a5c925bfaedf5f70
MiMo-V2.6-Flash-MOPD-Q2_K_S-00001-of-00002.gguf5.95 MB06907f217a77b33acde0b2d22c733ab781e269d5a73fa250998af9ef83440137
MiMo-V2.6-Flash-MOPD-Q2_K_S-00002-of-00002.gguf106 GB4f21f6083146630b2b633a8a68193c97817e2d102c30e7d92c8a7c8a6fd6949a
README.md1.17 KB0b7b542677f927ca3564381548ce940a53b66cbc2cb0a5c917ce4d94a9d04cd8
convert.log619 KB178a99453f52f48f13f7f1325ba80f1d283f35efcefcf32ef71626f255fe8807
dflash-MiMo-V2.6-Flash-MOPD-BF16.gguf5.44 GBcf7641b7db5072d7faccd2bd80930f7de96679b9b07e98042633fa7b1bceebef
dflash-MiMo-V2.6-Flash-MOPD-Q8_0.gguf2.89 GB81fd88b29a47b8558b6edbba34679d2c019a6ffa12fb977b610c79aaf4055aa9
mmproj-MiMo-V2.6-Flash-MOPD-BF16.gguf2.75 GB9b7d98d8afe2a6ae25635ecc490fb37883f912bf1d5648d1334fdc703e4a565e
mmproj-MiMo-V2.6-Flash-MOPD-Q8_0.gguf1.56 GB7fa58c0f20342fad37ef1962e8a9fd37ef834038b377e4f7e93f905e013e55db
mtp-MiMo-V2.6-Flash-MOPD-BF16.gguf4.48 GBc5361bd1152420c79f99de5ceae91c279df24a3c7aa516ef12d2d7b01587c771
mtp-MiMo-V2.6-Flash-MOPD-Q4_0.gguf1.26 GBda2532318663b31841bbf4af492cd47c6da80b4d496e32adcff912258d55fa71
mtp-MiMo-V2.6-Flash-MOPD-Q8_0.gguf2.38 GBc2189e7130727e698f3b744859dc763da730fd00f4c42a2be2c613fc9d918b97
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
c9d8697904 pinned now2026-11-15 04:50 UTC17 files · 420 GB

Use it

$ fw get ggml-org/MiMo-V2.6-Flash-MOPD-GGUF
# manifest sha256 2d989404e103… · 420 GB · 17 files
$ fw verify ./MiMo-V2.6-Flash-MOPD-GGUF ggml-org/MiMo-V2.6-Flash-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-Flash-MOPD-GGUF.json --dir ./MiMo-V2.6-Flash-MOPD-GGUF $ python3 fw.py verify ./MiMo-V2.6-Flash-MOPD-GGUF ./ggml-org__MiMo-V2.6-Flash-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-Flash-MOPD-GGUF --revision c9d8697904d2564708b5197d176543983b9d8db5 --local-dir ./MiMo-V2.6-Flash-MOPD-GGUF
llama.cppDownload one GGUF variant (mtp-MiMo-V2.6-Flash-MOPD-Q4_0, 1.26 GB), then serve it.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download ggml-org/MiMo-V2.6-Flash-MOPD-GGUF --include "mtp-MiMo-V2.6-Flash-MOPD-Q4_0*" --local-dir ./MiMo-V2.6-Flash-MOPD-GGUF $ llama-server -m ./MiMo-V2.6-Flash-MOPD-GGUF/mtp-MiMo-V2.6-Flash-MOPD-Q4_0.gguf
OllamaMake an Ollama model from the downloaded file.
$ printf 'FROM ./MiMo-V2.6-Flash-MOPD-GGUF/mtp-MiMo-V2.6-Flash-MOPD-Q4_0.gguf\n' > Modelfile $ ollama create mimo-v2.6-flash-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
0b7b542677f927ca3564381548ce940a53b66cbc2cb0a5c917ce4d94a9d04cd8
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-MOPD-GGUFDate: 2026-11-15Commit: c9d8697Signed: 2DC28CC7B26A283B ✓
Upstream
ggml-org/MiMo-V2.6-Flash-MOPD-GGUF
Pinned commit
c9d8697904d2564708b5197d176543983b9d8db5
Manifest
MiMo-V2.6-Flash-MOPD-GGUF.json · .minisig
Manifest sha256
2d989404e10399c5cfcc26cbaeb98806736ebaebe55ad34a70bd508bf8d49a71
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 04:50 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-MOPD-GGUF.json $ curl -O https://freeweights.allternit.com/manifests/ggml-org/MiMo-V2.6-Flash-MOPD-GGUF.json.minisig $ minisign -Vm MiMo-V2.6-Flash-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-Flash-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-Flash-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-Flash-MOPD-GGUF.json. Provenance. Takedown history: none.
Source
huggingface.co/ggml-org/MiMo-V2.6-Flash-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