CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.lfm / LFM2.5-8B-A1B-MLX-4bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.lfmSubject:

LFM2.5-8B-A1B-MLX-4bit

Date: 2026-11-15Commit: 146590aSigned: 2DC28CC7B26A283B ✓

Text generation model with 8.5B parameters. Safetensors weights, 4.78 GB in all. Published by mlx-community under LFM-1.0 (custom).

8.5B params4.78GBLFM2.5-8B-A1B-MLX-4bitsafetensorscustom terms
FactsParams8.5BSize4.78 GBFormatssafetensorsTasktext generationLicenseLFM-1.0 (custom)From sourcecustom termsread terms
# custom terms: read the license before you download
$ fw get mlx-community/LFM2.5-8B-A1B-MLX-4bit
# manifest sha256 c54504e2dfa3… · 4.78 GB · 9 files
$ fw verify ./LFM2.5-8B-A1B-MLX-4bit mlx-community/LFM2.5-8B-A1B-MLX-4bit
From sourceHosted (signed)mlx-community/LFM2.5-8B-A1B-MLX-4bitLast check: 2026-11-15 00:21 UTC
Run at homeGet help

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

Works with

Run24Fine-tune29Convert15Evaluate13Scan13Apps58
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
4.78 GB
Weights
4.76 GB (safetensors)
Parameters
8.5B
Formats
safetensors
Task
text generation
License
LFM-1.0 (custom) (custom)
Files
9, each with a sha256
Publisher
mlx-community
Added
2026-11-15
Section
alt.freeweights.lfm
Lineage

Original release from the publisher.

Base model: LiquidAI/LFM2.5-8B-A1B

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 00:21 UTCpassed

Model card

From the publisher at commit 146590a. Shown as plain text with links; images open at the publisher.

mlx-community/LFM2.5-8B-A1B-MLX-4bit#

This model mlx-community/LFM2.5-8B-A1B-MLX-4bit was converted to MLX format from LiquidAI/LFM2.5-8B-A1B using mlx-lm version 0.31.1.

lfm2_moe (Lfm2MoeForCausalLM): hybrid 18× double-gated short-conv + 6× GQA attention, 32-expert top-4 MoE — 8.3B total / 1.5B active, 128k context.

Use with mlx#

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/LFM2.5-8B-A1B-MLX-4bit")

prompt = "hello"
if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True)

response = generate(model, tokenizer, prompt=prompt, verbose=True)

License#

Derivative of LiquidAI/LFM2.5-8B-A1B under the LFM Open License v1.0 (lfm1.0); original model © Liquid AI. lfm1.0 commercial-use terms apply.

Files

9 files · 4.78 GBWeights 4.76 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 9 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md1.31 KBc83951024ca370557a38eff9a1bf8923958326001ceff35a5bc1883def8accf1
chat_template.jinja4.67 KBf434e8c96e6c0a63a022a3ad0a299bb94e58aa90e3c9ebe65034f8e8c6188aa9
config.json6.41 KBecbacb0de5bd94d0dce12413e15f7719cc865145cefb2fea46ade43e4b55b8ed
generation_config.json230 B8b9c36bf5e4c8a8254ec8292914834faa69b295a1e98e0fd93e3025a466730a6
model.safetensors4.76 GB01b990b43f3589fcf77e00cc6fe0a7d7d0b0056f28642d1c9f546cb09c03788e
model.safetensors.index.json43.3 KBf0ec30bf9efc38eae82000c2427a0849ce9f85f1d1f1effa4c8469288cf6bfe0
tokenizer.json17.9 MB695be7802a0e4b8a81048f0ff5ebb7fc811a0ba5a6be63dbb24deb5a81096f41
tokenizer_config.json315 Bb53c3caceb7fa0de424e1aa67b3cc5008cd2f8b8d2426a8fa221ef3cf1a949d5
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
146590a491 pinned now2026-11-15 00:21 UTC9 files · 4.78 GB

Use it

# custom terms: read the license before you download
$ fw get mlx-community/LFM2.5-8B-A1B-MLX-4bit
# manifest sha256 c54504e2dfa3… · 4.78 GB · 9 files
$ fw verify ./LFM2.5-8B-A1B-MLX-4bit mlx-community/LFM2.5-8B-A1B-MLX-4bit
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/mlx-community/LFM2.5-8B-A1B-MLX-4bit.json --dir ./LFM2.5-8B-A1B-MLX-4bit $ python3 fw.py verify ./LFM2.5-8B-A1B-MLX-4bit ./mlx-community__LFM2.5-8B-A1B-MLX-4bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/LFM2.5-8B-A1B-MLX-4bit --revision 146590a491db88581884033023f51f6b49a27b89 --local-dir ./LFM2.5-8B-A1B-MLX-4bit
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForCausalLM, AutoTokenizer tok = AutoTokenizer.from_pretrained("mlx-community/LFM2.5-8B-A1B-MLX-4bit", revision="146590a491db88581884033023f51f6b49a27b89") model = AutoModelForCausalLM.from_pretrained("mlx-community/LFM2.5-8B-A1B-MLX-4bit", revision="146590a491db88581884033023f51f6b49a27b89", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/LFM2.5-8B-A1B-MLX-4bit --revision 146590a491db88581884033023f51f6b49a27b89
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
c83951024ca370557a38eff9a1bf8923958326001ceff35a5bc1883def8accf1
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: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.lfmSubject: LFM2.5-8B-A1B-MLX-4bitDate: 2026-11-15Commit: 146590aSigned: 2DC28CC7B26A283B ✓
Upstream
mlx-community/LFM2.5-8B-A1B-MLX-4bit
Pinned commit
146590a491db88581884033023f51f6b49a27b89
Manifest
LFM2.5-8B-A1B-MLX-4bit.json · .minisig
Manifest sha256
c54504e2dfa3b19ab206625f66ea8b627959c9c25dc7650df788f98a662f21c5
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 00:21 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/LFM2.5-8B-A1B-MLX-4bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/LFM2.5-8B-A1B-MLX-4bit.json.minisig $ minisign -Vm LFM2.5-8B-A1B-MLX-4bit.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/LFM2.5-8B-A1B (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 mlx-community/LFM2.5-8B-A1B-MLX-4bit
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. LFM2.5-8B-A1B-MLX-4bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/LFM2.5-8B-A1B-MLX-4bit

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