CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.lfm / tinyLFM3-Omni-for-testing-gguf
From: ggml-org <huggingface.co/ggml-org>Newsgroups: alt.freeweights.lfmSubject:

tinyLFM3-Omni-for-testing-gguf

Date: 2026-11-15Commit: 0d21fb0Signed: 2DC28CC7B26A283B ✓

Model. Gguf weights, 39.3 MB in all. Published by ggml-org under LFM-1.0 (custom).

lfm39.3MBtinyLFM3-Omni-for-testing-ggufggufcustom terms
FactsParamsnot statedSize39.3 MBFormatsggufTasknot taggedLicenseLFM-1.0 (custom)From sourcecustom termsread terms
# custom terms: read the license before you download
$ fw get ggml-org/tinyLFM3-Omni-for-testing-gguf
# manifest sha256 179a7fc1bc7d… · 39.3 MB · 7 files
$ fw verify ./tinyLFM3-Omni-for-testing-gguf ggml-org/tinyLFM3-Omni-for-testing-gguf
From sourceHosted (signed)ggml-org/tinyLFM3-Omni-for-testing-ggufLast check: 2026-11-15 00:18 UTC
Run at homeGet help

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

Works with

Run11Convert1Scan1

Convert with

ggml

Scan with

ModelScan
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
39.3 MB
Weights
20.0 MB (GGUF)
Parameters
not stated
Formats
gguf
Task
not tagged
License
LFM-1.0 (custom) (custom)
Files
7, each with a sha256
Publisher
ggml-org
Added
2026-11-15
Section
alt.freeweights.lfm
Lineage

Original release from the publisher.

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 00:18 UTCpassed

Model card

From the publisher at commit 0d21fb0. Shown as plain text with links; images open at the publisher.

tinyLFM3-Omni-for-testing#

Warning. This is a modified, damaged copy of LiquidAI/LFM3-Omni-2B, made only to test software. Its output is gibberish. Do not use it for anything else.

It keeps the architecture of LFM3-Omni, so it runs the same code paths as the real model in llama.cpp (TTS, ASR, realtime audio and image input), but it is small enough for CI.

Use the real model instead: https://huggingface.co/ggml-org/LFM3-Omni-2B-GGUF

Changes from the original model#

Sliced from the safetensors with slice_lfm3omni.py, which follows the slice-model skill of llama.cpp, then converted with convert_hf_to_gguf.py:

  • Text model: 4 of 24 layers (0, 2, 3, 4), hidden size 2048 -> 256, heads 16 -> 2, KV heads 4 -> 1, FFN 7680 -> 256
  • Audio encoder: 3 of 17 layers (0, 2, 3), FFN 1792 -> 256
  • Depthformer: 1 of 3 layers, hidden size 1024 -> 128, heads 32 -> 4, KV heads 8 -> 1, FFN 2816 -> 256
  • Audio codec: all 8 layers (the loader requires it), FFN 2304 -> 256
  • Vision encoder: 2 of 14 layers (0, 2), hidden size 1024 -> 256, heads 16 -> 4, KV heads 8 -> 2, FFN 2560 -> 256, projector 4096 -> 256

Then finish_gguf.py made these changes:

  • Weights quantized to Q2_K, Q4_K and Q4_0
  • Added the asr chat template of LFM3-Audio, which the original model does not have. This enables the live transcription path (/v1/realtime?intent=transcription) for testing

License#

Derived from LFM3-Omni-2B by Liquid AI, under the LFM Open License v1.0.

Files

7 files · 39.3 MBWeights 20.0 MB (GGUF). Sizes and sha256 from the signed manifest.
Hide all 7 files with their sha256
FileSizesha256
.gitattributes1.67 KBb03a920472556fc3b8d9d0e3e0a35b52959135e1e5a27f11e1b26e077e3cdeac
LICENSE10.6 KB4d28ca14dedc0b3d0fcc2b3339f0e79931faa33874f3d24f522183a8fc70068c
README.md1.66 KBe508a704c82e66dc0480cda7175a2bf4a6e2aea947308350ec07419634c9d9fe
finish_gguf.py3.50 KBe6ca0bd5c70def4df589492b60b85307e3163793b37adad524f5cb514acbe6c9
mmproj-tinyLFM3-Omni-for-testing-Q2_K.gguf19.3 MB8978a601f2b7c41a85dc16a4aff6d90cdc1ea01f957cb2ad33c7ad0505ac780b
slice_lfm3omni.py9.71 KBdb7619f769e0cb344aed79851da288ac9406be51355cab618a43a6e28b371341
tinyLFM3-Omni-for-testing-Q2_K.gguf20.0 MBc93c250c4a6a8da743328f8a503fa74d0b56f0efc103db08cb29aeae2514297c
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
0d21fb0532 pinned now2026-11-15 00:18 UTC7 files · 39.3 MB

Use it

# custom terms: read the license before you download
$ fw get ggml-org/tinyLFM3-Omni-for-testing-gguf
# manifest sha256 179a7fc1bc7d… · 39.3 MB · 7 files
$ fw verify ./tinyLFM3-Omni-for-testing-gguf ggml-org/tinyLFM3-Omni-for-testing-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/tinyLFM3-Omni-for-testing-gguf.json --dir ./tinyLFM3-Omni-for-testing-gguf $ python3 fw.py verify ./tinyLFM3-Omni-for-testing-gguf ./ggml-org__tinyLFM3-Omni-for-testing-gguf.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download ggml-org/tinyLFM3-Omni-for-testing-gguf --revision 0d21fb0532bb81b5d6564c823ccd0c3df53b7ba7 --local-dir ./tinyLFM3-Omni-for-testing-gguf
llama.cppDownload one GGUF variant (tinyLFM3-Omni-for-testing-Q2_K, 20.0 MB), then serve it.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download ggml-org/tinyLFM3-Omni-for-testing-gguf --include "tinyLFM3-Omni-for-testing-Q2_K*" --local-dir ./tinyLFM3-Omni-for-testing-gguf $ llama-server -m ./tinyLFM3-Omni-for-testing-gguf/tinyLFM3-Omni-for-testing-Q2_K.gguf
OllamaMake an Ollama model from the downloaded file.
$ printf 'FROM ./tinyLFM3-Omni-for-testing-gguf/tinyLFM3-Omni-for-testing-Q2_K.gguf\n' > Modelfile $ ollama create tinylfm3-omni-for-testing-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
LICENSE
Text sha256
4d28ca14dedc0b3d0fcc2b3339f0e79931faa33874f3d24f522183a8fc70068c
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: tinyLFM3-Omni-for-testing-ggufDate: 2026-11-15Commit: 0d21fb0Signed: 2DC28CC7B26A283B ✓
Upstream
ggml-org/tinyLFM3-Omni-for-testing-gguf
Pinned commit
0d21fb0532bb81b5d6564c823ccd0c3df53b7ba7
Manifest
tinyLFM3-Omni-for-testing-gguf.json · .minisig
Manifest sha256
179a7fc1bc7d661eedc2f0f3a716d9e454be6ebdfe3e6b37ef0cb5ccda2a5c20
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 00:18 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/ggml-org/tinyLFM3-Omni-for-testing-gguf.json $ curl -O https://freeweights.allternit.com/manifests/ggml-org/tinyLFM3-Omni-for-testing-gguf.json.minisig $ minisign -Vm tinyLFM3-Omni-for-testing-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

No related models in this catalog.Nothing here lists this model as its parent, and it names no parent.
Get it
Read license, then download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download ggml-org/tinyLFM3-Omni-for-testing-gguf
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. tinyLFM3-Omni-for-testing-gguf.json. Provenance. Takedown history: none.
Source
huggingface.co/ggml-org/tinyLFM3-Omni-for-testing-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