alt.freeweights.minicpm / MiniCPM-o-2_6-gguf

From: openbmb <huggingface.co/openbmb>Newsgroups: alt.freeweights.minicpmSubject:

MiniCPM-o-2_6-gguf

Date: 2026-11-15Commit: 4659f57Signed: 2DC28CC7B26A283B ✓

Any to any model. Gguf weights, 65.6 GB in all. Published by openbmb under Apache-2.0.

minicpm65.6GBMiniCPM-o-2_6-ggufggufpermissive

FactsParamsnot statedSize65.6 GBFormatsggufTaskany to anyLicenseApache-2.0From sourcepermissive

$ fw get openbmb/MiniCPM-o-2_6-gguf
# manifest sha256 eab2dd2828bd… · 65.6 GB · 13 files
$ fw verify ./MiniCPM-o-2_6-gguf openbmb/MiniCPM-o-2_6-gguf

From sourceHosted (signed)openbmb/MiniCPM-o-2_6-ggufLast check: 2026-11-15 04:52 UTC

Run at home Get help

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

Quantized of MiniCPM-o-2_6.

Works with

Run11 Convert1 Scan1

Runs with

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

Ollama

llama.cpp LocalAI

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

Convert with

ggml

Scan with

ModelScan

Overview Model card Files Use it License Provenance Model tree

Overview

Size: 65.6 GB
Weights: 4.43 GB (smallest of 10 GGUF variants)
Parameters: not stated
Formats: gguf
Task: any to any
License: Apache-2.0 (permissive)
Files: 13, each with a sha256
Publisher: openbmb
Added: 2026-11-15
Section: alt.freeweights.minicpm

Lineage

Original release from the publisher.

Base model: openbmb/MiniCPM-o-2_6

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	2026-11-15 04:52 UTC	passed

Model card

From the publisher at commit 4659f57. Shown as plain text with links; images open at the publisher.

A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone#

GitHub | MiniCPM Wiki(Chinese) | Online Demo | Technical Blog | Join Us

MiniCPM-o 2.6#

This repository contains the MiniCPM-o 2.6 model weights in GGUF format, used for llama.cpp.

Currently, this readme only supports minicpm-omni's vision capabilities, and we will update the full-mode support as soon as possible.

Prepare models and code#

Download MiniCPM-o-2_6 PyTorch model from huggingface to "MiniCPM-o-2_6" folder.

Clone llama.cpp:

git clone git@github.com:OpenBMB/llama.cpp.git
cd llama.cpp
git checkout minicpm-omni

Usage of MiniCPM-o 2.6#

Convert PyTorch model to gguf files (You can also download the converted gguf by us)

python ./examples/llava/minicpmv-surgery.py -m ../MiniCPM-o-2_6
python ./examples/llava/minicpmv-convert-image-encoder-to-gguf.py -m ../MiniCPM-o-2_6 --minicpmv-projector ../MiniCPM-o-2_6/minicpmv.projector --output-dir ../MiniCPM-o-2_6/ --image-mean 0.5 0.5 0.5 --image-std 0.5 0.5 0.5 --minicpmv_version 4
python ./convert_hf_to_gguf.py ../MiniCPM-o-2_6/model

# quantize int4 version
./llama-quantize ../MiniCPM-o-2_6/model/ggml-model-f16.gguf ../MiniCPM-o-2_6/model/ggml-model-Q4_K_M.gguf Q4_K_M

Build llama.cpp using CMake: https://github.com/ggerganov/llama.cpp/blob/master/docs/build.md

cmake -B build
cmake --build build --config Release

Inference on Linux or Mac

# run f16 version
./llama-minicpmv-cli -m ../MiniCPM-o-2_6/model/ggml-model-f16.gguf --mmproj ../MiniCPM-o-2_6/mmproj-model-f16.gguf -c 4096 --temp 0.7 --top-p 0.8 --top-k 100 --repeat-penalty 1.05 --image xx.jpg -p "What is in the image?"

# run quantized int4 version
./llama-minicpmv-cli -m ../MiniCPM-o-2_6/model/ggml-model-Q4_K_M.gguf --mmproj ../MiniCPM-o-2_6/mmproj-model-f16.gguf -c 4096 --temp 0.7 --top-p 0.8 --top-k 100 --repeat-penalty 1.05 --image xx.jpg  -p "What is in the image?"

# or run in interactive mode
./llama-minicpmv-cli -m ../MiniCPM-o-2_6/model/ggml-model-Q4_K_M.gguf --mmproj ../MiniCPM-o-2_6/mmproj-model-f16.gguf -c 4096 --temp 0.7 --top-p 0.8 --top-k 100 --repeat-penalty 1.05 --image xx.jpg -i

Files

13 files · 65.6 GBWeights 4.43 GB (smallest of 10 GGUF variants). Sizes and sha256 from the signed manifest.

Hide all 13 files with their sha256

File	Size	sha256
.gitattributes	2.15 KB	b41e7da9dd2a90c0ce19c8a9657c02b6a3ef17f5d5039e7cf7021b8bd696f179
Model-7.6B-F16.gguf	15.2 GB	d43cdc076bc30c218ab811f910063222afbb4b8b1303a9507c7257142569a6a0
Model-7.6B-Q4_0.gguf	4.43 GB	6b1d269cbaf94788a52eea403487c9c12a06330411d56898cf5a7e02dd623978
Model-7.6B-Q4_1.gguf	4.87 GB	1e0c314fdb1ab2d5eb648a37247e7f22fae5fa6f0fa159f7d1af37feee2566c2
Model-7.6B-Q4_K_M.gguf	4.68 GB	4f635fc0c0bb88d50ccd9cf1f1e5892b5cb085ff88fe0d8e1148fd9a8a836bc2
Model-7.6B-Q4_K_S.gguf	4.46 GB	6d28c300dab7c224f9b34afcca0e0413c985846482f62e49b2cef109f82af926
Model-7.6B-Q5_0.gguf	5.31 GB	5a0081fff534c8d531e5663323942c780722b181321ba352eb81bf4521f93d73
Model-7.6B-Q5_1.gguf	5.76 GB	01308f619a2cb11b2fad69af9732eb5d97c63e89da754a02a1130670e8e5081b
Model-7.6B-Q5_K_M.gguf	5.44 GB	95c49d0b06172fea29f5ac5cdd374f98915aa4c650332c2e23734a8aeb36e62e
Model-7.6B-Q6_K.gguf	6.25 GB	9395c100963ab84657ab18bd88e249327d87ffad2cabadce463da73ebd7ff89b
Model-7.6B-Q8_0.gguf	8.10 GB	b13bd996700f60faacb798321dbc76de7c5bb6eb9a05510650f223c8f99bf359
README.md	2.90 KB	8a4a9d654c619355a0bd780d388255a61dd6554ca2066721cf5d780b625f95e8
mmproj-model-f16.gguf	1.04 GB	efa4f7d96aa0f838f2023fc8d28e519179b16f1106777fa9280b32628191aa3e

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

Upstream commit	Date	Contents
4659f57732 pinned now	2026-11-15 04:52 UTC	13 files · 65.6 GB

Use it

$ fw get openbmb/MiniCPM-o-2_6-gguf
# manifest sha256 eab2dd2828bd… · 65.6 GB · 13 files
$ fw verify ./MiniCPM-o-2_6-gguf openbmb/MiniCPM-o-2_6-gguf

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

$ python3 fw.py get https://freeweights.allternit.com/manifests/openbmb/MiniCPM-o-2_6-gguf.json --dir ./MiniCPM-o-2_6-gguf
$ python3 fw.py verify ./MiniCPM-o-2_6-gguf ./openbmb__MiniCPM-o-2_6-gguf.json

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

$ HF_ENDPOINT=https://freeweights.allternit.com hf download openbmb/MiniCPM-o-2_6-gguf --revision 4659f57732eddf7996cdafbd1a646c1db5ff1084 --local-dir ./MiniCPM-o-2_6-gguf

llama.cppDownload one GGUF variant (Model-7.6B-Q4_0, 4.43 GB), then serve it.

$ HF_ENDPOINT=https://freeweights.allternit.com hf download openbmb/MiniCPM-o-2_6-gguf --include "Model-7.6B-Q4_0*" --local-dir ./MiniCPM-o-2_6-gguf
$ llama-server -m ./MiniCPM-o-2_6-gguf/Model-7.6B-Q4_0.gguf

OllamaMake an Ollama model from the downloaded file.

$ printf 'FROM ./MiniCPM-o-2_6-gguf/Model-7.6B-Q4_0.gguf\n' > Modelfile
$ ollama create minicpm-o-2-6-gguf -f Modelfile

Run at home

License

Name: Apache License 2.0
Id: Apache-2.0
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: 8a4a9d654c619355a0bd780d388255a61dd6554ca2066721cf5d780b625f95e8
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: openbmb <huggingface.co/openbmb>Newsgroups: alt.freeweights.minicpmSubject: MiniCPM-o-2_6-ggufDate: 2026-11-15Commit: 4659f57Signed: 2DC28CC7B26A283B ✓

Upstream: openbmb/MiniCPM-o-2_6-gguf
Pinned commit: 4659f57732eddf7996cdafbd1a646c1db5ff1084
Manifest: MiniCPM-o-2_6-gguf.json · .minisig
Manifest sha256: eab2dd2828bdebafe4ce030822541f26bb4098da2861bfbda6261427b086856b
Signature: minisign, Ed25519, key 2DC28CC7B26A283B
Created: 2026-11-15 04:52 UTC
Generator: freeweights-manifest/0.1.0
Takedowns: None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/openbmb/MiniCPM-o-2_6-gguf.json
$ curl -O https://freeweights.allternit.com/manifests/openbmb/MiniCPM-o-2_6-gguf.json.minisig
$ minisign -Vm MiniCPM-o-2_6-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

openbmb/MiniCPM-o-2_6 · 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 openbmb/MiniCPM-o-2_6-gguf

Open in Freeweights Studio

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

Signed manifest

minisign, key 2DC28CC7B26A283B. MiniCPM-o-2_6-gguf.json. Provenance. Takedown history: none.

Source

huggingface.co/openbmb/MiniCPM-o-2_6-gguf

Related models

All of alt.freeweights.minicpm →

From: openbmb <huggingface.co/openbmb>Subject: AgentCPM-Explore-GGUF

From: openbmb <huggingface.co/openbmb>Subject: AgentCPM-Report

From: openbmb <huggingface.co/openbmb>Subject: AgentCPM-Report-GGUF

From: openbmb <huggingface.co/openbmb>Subject: BitCPM-CANN-0.5B-gguf

From: openbmb <huggingface.co/openbmb>Subject: BitCPM-CANN-1B-gguf

From: openbmb <huggingface.co/openbmb>Subject: BitCPM-CANN-3B-gguf