CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.lfm / LFM3-Omni-2B-GGUF
From: ggml-org <huggingface.co/ggml-org>Newsgroups: alt.freeweights.lfmSubject:

LFM3-Omni-2B-GGUF

Date: 2026-11-15Commit: 0b6888cSigned: 2DC28CC7B26A283B ✓

Any to any model. Gguf weights, 7.87 GB in all. Published by ggml-org under LFM-1.0 (custom).

lfm7.87GBLFM3-Omni-2B-GGUFggufcustom terms
FactsParamsnot statedSize7.87 GBFormatsggufTaskany to anyLicenseLFM-1.0 (custom)From sourcecustom termsread terms
# custom terms: read the license before you download
$ fw get ggml-org/LFM3-Omni-2B-GGUF
# manifest sha256 2f06d543e983… · 7.87 GB · 9 files
$ fw verify ./LFM3-Omni-2B-GGUF ggml-org/LFM3-Omni-2B-GGUF
From sourceHosted (signed)ggml-org/LFM3-Omni-2B-GGUFLast check: 2026-11-15 00:17 UTC
Run at homeGet help

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

Quantized of LFM3-Omni-2B.

Works with

Run11Convert1Scan1

Convert with

ggml

Scan with

ModelScan
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
7.87 GB
Weights
1.10 GB (smallest of 3 GGUF variants)
Parameters
not stated
Formats
gguf
Task
any to any
License
LFM-1.0 (custom) (custom)
Files
9, each with a sha256
Publisher
ggml-org
Added
2026-11-15
Section
alt.freeweights.lfm
Lineage

Original release from the publisher.

Base model: LiquidAI/LFM3-Omni-2B

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 00:17 UTCpassed

Model card

From the publisher at commit 0b6888c. Shown as plain text with links; images open at the publisher.

LFM3-Omni-2B#

Run with https://llama.app

llama serve -hf ggml-org/LFM3-Omni-2B-GGUF
Source models#
Notes#

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

Files

9 files · 7.87 GBWeights 1.10 GB (smallest of 3 GGUF variants). Sizes and sha256 from the signed manifest.
Hide all 9 files with their sha256
FileSizesha256
.gitattributes1.83 KBe2ff822e8cbf38564c8a4ea9fd5ecc05bec734b1777101b35c2e92c843d3012a
.src_sha49 B1459e468f49c28a2ca0658f9c72ab73a805c0c213786688b9ed1220f3529abba
LFM3-Omni-2B-BF16.gguf3.47 GBdd504610f4fcddd44a62f70fed99d842d28a88ce81fb0acda09fca56397a4eaf
LFM3-Omni-2B-Q4_K_M.gguf1.10 GBcc0879a5ae593a84ea4681535feb30377f1c867f8feda77b3b5b68b7881dea06
LFM3-Omni-2B-Q8_0.gguf1.85 GB40d27b13e500963468f1fd1099863464a4a5e8f4682e934f9be8b54641b8c0c7
README.md944 B423beaf7be3843483899044f2a87db9f0e306c1880fa85b8f5a87cf64c1ba18f
convert.log230 KB057c1a689b045cf130cef2ccf13199c2a34b9ef04bbdd6f96b102da6abf5f3f2
mmproj-LFM3-Omni-2B-BF16.gguf950 MB3e991800f8357d645f3c9aef6054df5df5237f1b88ea656a5b5b3c91418f8409
mmproj-LFM3-Omni-2B-Q8_0.gguf507 MB279fb3110acc6c20876016f92487006d95507fccb0699b0ef22ae19cc417c79e
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
0b6888cd0b pinned now2026-11-15 00:17 UTC9 files · 7.87 GB

Use it

# custom terms: read the license before you download
$ fw get ggml-org/LFM3-Omni-2B-GGUF
# manifest sha256 2f06d543e983… · 7.87 GB · 9 files
$ fw verify ./LFM3-Omni-2B-GGUF ggml-org/LFM3-Omni-2B-GGUF
Terms that come with these files. LFM 1.0: commercial use only for organisations under US$10M annual revenue. Keep a copy of the license with the files.
Custom license (custom). Read the license text first. Open this panel to show the commands once you accept its terms.
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/ggml-org/LFM3-Omni-2B-GGUF.json --dir ./LFM3-Omni-2B-GGUF $ python3 fw.py verify ./LFM3-Omni-2B-GGUF ./ggml-org__LFM3-Omni-2B-GGUF.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download ggml-org/LFM3-Omni-2B-GGUF --revision 0b6888cd0b7ac8962cb8b125f0bf087c3178de5f --local-dir ./LFM3-Omni-2B-GGUF
llama.cppDownload one GGUF variant (LFM3-Omni-2B-Q4_K_M, 1.10 GB), then serve it.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download ggml-org/LFM3-Omni-2B-GGUF --include "LFM3-Omni-2B-Q4_K_M*" --local-dir ./LFM3-Omni-2B-GGUF $ llama-server -m ./LFM3-Omni-2B-GGUF/LFM3-Omni-2B-Q4_K_M.gguf
OllamaMake an Ollama model from the downloaded file.
$ printf 'FROM ./LFM3-Omni-2B-GGUF/LFM3-Omni-2B-Q4_K_M.gguf\n' > Modelfile $ ollama create lfm3-omni-2b-gguf -f Modelfile
Run at home

License

Name
LFM Open License v1.0
Id
LicenseRef-LFM-1.0
Class
Custom terms
Redistribution
click-through
Listing
Hosted (signed)
Terms
LFM 1.0: commercial use only for organisations under US$10M annual revenue. Keep a copy of the license with the files.
Decided
License as declared by the publisher. No person read it. 2026-11-15
Text in
README.md
Text sha256
423beaf7be3843483899044f2a87db9f0e306c1880fa85b8f5a87cf64c1ba18f
Terms gate
Yes. The commands stay folded until you open them after reading 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.lfmSubject: LFM3-Omni-2B-GGUFDate: 2026-11-15Commit: 0b6888cSigned: 2DC28CC7B26A283B ✓
Upstream
ggml-org/LFM3-Omni-2B-GGUF
Pinned commit
0b6888cd0b7ac8962cb8b125f0bf087c3178de5f
Manifest
LFM3-Omni-2B-GGUF.json · .minisig
Manifest sha256
2f06d543e98312ccbcfcda4023a969e8cffad2c6539a221736e6835edf258eb9
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 00:17 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/ggml-org/LFM3-Omni-2B-GGUF.json $ curl -O https://freeweights.allternit.com/manifests/ggml-org/LFM3-Omni-2B-GGUF.json.minisig $ minisign -Vm LFM3-Omni-2B-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

LiquidAI/LFM3-Omni-2B · this model is a quantization of it

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

Get it
Read license, then download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download ggml-org/LFM3-Omni-2B-GGUF
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. LFM3-Omni-2B-GGUF.json. Provenance. Takedown history: none.
Source
huggingface.co/ggml-org/LFM3-Omni-2B-GGUF

Related models

All of alt.freeweights.lfm →
From: LiquidAI <huggingface.co/LiquidAI>Subject: LFM2-1.2B
From: LiquidAI <huggingface.co/LiquidAI>Subject: LFM2-1.2B-Extract
From: LiquidAI <huggingface.co/LiquidAI>Subject: LFM2-1.2B-RAG
From: LiquidAI <huggingface.co/LiquidAI>Subject: LFM2-1.2B-Tool
From: LiquidAI <huggingface.co/LiquidAI>Subject: LFM2-2.6B
From: LiquidAI <huggingface.co/LiquidAI>Subject: LFM2-2.6B-Exp