alt.freeweights.lfm / LFM2.5-24B-A2B-GGUF

From:

ggml-org <huggingface.co/ggml-org>Newsgroups: alt.freeweights.lfmSubject:

LFM2.5-24B-A2B-GGUF

Date: 2026-11-15Commit: 06fd877Signed: 2DC28CC7B26A283B ✓

Text generation model. Gguf weights, 88.0 GB in all. Published by ggml-org under LFM-1.0 (custom).

lfm

88.0GBLFM2.5-24B-A2B-GGUFggufcustom terms

FactsParamsnot statedSize88.0 GBFormatsggufTasktext generationLicenseLFM-1.0 (custom)From sourcecustom termsread terms

# custom terms: read the license before you download
$ fw get ggml-org/LFM2.5-24B-A2B-GGUF
# manifest sha256 c3b9b2e3504f… · 88.0 GB · 7 files
$ fw verify ./LFM2.5-24B-A2B-GGUF ggml-org/LFM2.5-24B-A2B-GGUF

From sourceHosted (signed)ggml-org/LFM2.5-24B-A2B-GGUFLast check: 2026-11-15 00:17 UTC

Run at home Get help

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

Works with

Run14 Convert1 Evaluate13 Scan12 Apps58

Runs with

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

Text Generation WebUI mistral.rs

Ollama

llama.cpp LocalAI

BitNet llamafile gpu-unlock KoboldCpp PocketPal AI llama-swap ik_llama.cpp

Show all 14

RamaLama Maid

Convert with

ggml

Evaluate with

Opik DeepEval Ragas lm-evaluation-harness OpenCompass SWE-bench

simple-evals TruLens HELM

LightEval

Evaluate Weave

Show all 13

Autoevals

Scan with

promptfoo garak Guardrails NeMo Guardrails Giskard DeepTeam AI Fairness 360 Fairlearn Detoxify MCP Scanner AgentDojo ModelScan

Overview Model card Files Use it License Provenance Model tree

Overview

Size: 88.0 GB
Weights: 14.5 GB (smallest of 3 GGUF variants)
Parameters: not stated
Formats: gguf
Task: text generation
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.

Base model: LiquidAI/LFM2.5-24B-A2B

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 00:17 UTC	passed

Model card

From the publisher at commit 06fd877. Shown as plain text with links; images open at the publisher.

LFM2.5-24B-A2B#

Run with https://llama.app

llama serve -hf ggml-org/LFM2.5-24B-A2B-GGUF

Source models#

https://huggingface.co/LiquidAI/LFM2.5-24B-A2B

Notes#

Q8_0 and Q4_K_M use the same quantization as LiquidAI's own GGUFs: https://huggingface.co/LiquidAI/LFM2.5-24B-A2B-GGUF
For a smaller build, LiquidAI also publishes a Quantization-Aware Distillation (QAD) Q4_0, trained to recover the accuracy lost to Q4_0 quantization.

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

Files

7 files · 88.0 GBWeights 14.5 GB (smallest of 3 GGUF variants). Sizes and sha256 from the signed manifest.

Hide all 7 files with their sha256

File	Size	sha256
.gitattributes	1.70 KB	059134f832cca0f0b925f20ce577a434c67f252a5682a04cf8d43ff2cd55179b
.src_sha	49 B	0a2c7f02384aae4122f95003a67bb61e48a22c0328b2a247b1346f9b90c5d991
LFM2.5-24B-A2B-BF16.gguf	48.0 GB	6a8ed0f8e92ff4e0644f3795899e4a2950c38ed483937894e5209d6887e64ede
LFM2.5-24B-A2B-Q4_K_M.gguf	14.5 GB	5c286f305e7f485c00b86db6faf75876cab96ecbca024b1931324d3be8351272
LFM2.5-24B-A2B-Q8_0.gguf	25.5 GB	d7c34c7125934d81545bcdfe0305f1e876c140a37b5ad8ae834dc682eb0a6ca9
README.md	770 B	67c4fc0269723bb3ee2ef2730c3eadfd676bcb0be53fd0e976218d71aa2ec143
convert.log	186 KB	bb9bf8fa2af9f3c46c283d2446f992ac9bc3aff70787913599b609aab3fecd35

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

Upstream commit	Date	Contents
06fd877f89 pinned now	2026-11-15 00:17 UTC	7 files · 88.0 GB

Use it

# custom terms: read the license before you download
$ fw get ggml-org/LFM2.5-24B-A2B-GGUF
# manifest sha256 c3b9b2e3504f… · 88.0 GB · 7 files
$ fw verify ./LFM2.5-24B-A2B-GGUF ggml-org/LFM2.5-24B-A2B-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/LFM2.5-24B-A2B-GGUF.json --dir ./LFM2.5-24B-A2B-GGUF
$ python3 fw.py verify ./LFM2.5-24B-A2B-GGUF ./ggml-org__LFM2.5-24B-A2B-GGUF.json

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

$ HF_ENDPOINT=https://freeweights.allternit.com hf download ggml-org/LFM2.5-24B-A2B-GGUF --revision 06fd877f89aff75ad7f874f9cda22e7e71fbb910 --local-dir ./LFM2.5-24B-A2B-GGUF

llama.cppDownload one GGUF variant (LFM2.5-24B-A2B-Q4_K_M, 14.5 GB), then serve it.

$ HF_ENDPOINT=https://freeweights.allternit.com hf download ggml-org/LFM2.5-24B-A2B-GGUF --include "LFM2.5-24B-A2B-Q4_K_M*" --local-dir ./LFM2.5-24B-A2B-GGUF
$ llama-server -m ./LFM2.5-24B-A2B-GGUF/LFM2.5-24B-A2B-Q4_K_M.gguf

OllamaMake an Ollama model from the downloaded file.

$ printf 'FROM ./LFM2.5-24B-A2B-GGUF/LFM2.5-24B-A2B-Q4_K_M.gguf\n' > Modelfile
$ ollama create lfm2.5-24b-a2b-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: 67c4fc0269723bb3ee2ef2730c3eadfd676bcb0be53fd0e976218d71aa2ec143
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: LFM2.5-24B-A2B-GGUFDate: 2026-11-15Commit: 06fd877Signed: 2DC28CC7B26A283B ✓

Upstream: ggml-org/LFM2.5-24B-A2B-GGUF
Pinned commit: 06fd877f89aff75ad7f874f9cda22e7e71fbb910
Manifest: LFM2.5-24B-A2B-GGUF.json · .minisig
Manifest sha256: c3b9b2e3504fad765c287b440acbdf8595193edc9251174098181dbdcc53b368
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/LFM2.5-24B-A2B-GGUF.json
$ curl -O https://freeweights.allternit.com/manifests/ggml-org/LFM2.5-24B-A2B-GGUF.json.minisig
$ minisign -Vm LFM2.5-24B-A2B-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/LFM2.5-24B-A2B (not in this catalog) · 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/LFM2.5-24B-A2B-GGUF

Open in Freeweights Studio

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

Signed manifest

minisign, key 2DC28CC7B26A283B. LFM2.5-24B-A2B-GGUF.json. Provenance. Takedown history: none.

Source

huggingface.co/ggml-org/LFM2.5-24B-A2B-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