alt.freeweights.lfm / LFM2-2.6B-4bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.lfmSubject:

LFM2-2.6B-4bit

Date: 2026-11-15Commit: 493071eSigned: 2DC28CC7B26A283B ✓

Text generation model with 2.6B parameters. Safetensors weights, 1.45 GB in all. Published by mlx-community under LFM-1.0 (custom).

2.6B params1.45GBLFM2-2.6B-4bitsafetensorscustom terms
FactsParams2.6BSize1.45 GBFormatssafetensorsTasktext generationLicenseLFM-1.0 (custom)From sourcecustom termsread terms
# custom terms: read the license before you download
$ fw get mlx-community/LFM2-2.6B-4bit
# manifest sha256 5eb2c8ff9e85… · 1.45 GB · 10 files
$ fw verify ./LFM2-2.6B-4bit mlx-community/LFM2-2.6B-4bit
From sourceHosted (signed)mlx-community/LFM2-2.6B-4bitLast check: 2026-11-15 00:21 UTC

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

Quantized of LFM2-2.6B.

Works with

Overview

Size
1.45 GB
Weights
1.45 GB (safetensors)
Parameters
2.6B
Formats
safetensors
Task
text generation
License
LFM-1.0 (custom) (custom)
Files
10, each with a sha256
Publisher
mlx-community
Added
2026-11-15
Section
alt.freeweights.lfm
Lineage

Original release from the publisher.

Base model: LiquidAI/LFM2-2.6B

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 493071e. Shown as plain text with links; images open at the publisher.

mlx-community/LFM2-2.6B-4bit#

This model mlx-community/LFM2-2.6B-4bit was converted to MLX format from LiquidAI/LFM2-2.6B using mlx-lm version 0.28.0.

Use with mlx#

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/LFM2-2.6B-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)

Files

10 files · 1.45 GBWeights 1.45 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 10 files with their sha256
FileSizesha256
.gitattributes1.52 KB11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361
README.md918 B7e170a6814f0e13f7c3f05e905e083c66c2a3e935e8be4bd5b48fb371fb2534b
chat_template.jinja1.30 KB89e790f027916b5a2bca145a6a8454e06ffc7a5043bf3b6d97829aff86bb543f
config.json1.88 KBcb3a98946262ce725ab7a2e9e880a178914895a8a5a73f8dec17f21b7b55128f
generation_config.json137 B93a20028b6fb1f83d8ab33bcad0dd3878f74975dd4881e5435bc6d5dd21915bc
model.safetensors1.45 GB7cebcdbbcd0ff753616a22fb8dfe98f9cdc11a256430c5b87fbec09342e2cf46
model.safetensors.index.json42.0 KBd7296e9210effeba57519cd9768451b0271ccfc70bdd479c34c8f6f98df3f0d5
special_tokens_map.json434 B742aefe2b7dec496e8caffdba03a75d0c1a9925d53bd3f3e0d388c96b591b6f4
tokenizer.json4.73 MB89f0c8a6a1a96dd707d2efd06d815aa86123aaaad8328dda13188fcad6e25592
tokenizer_config.json91.6 KB769f519f71235c6c212773284c8e369e2c449921d818dfa623d65a1c4b05b987
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
493071ebca pinned now2026-11-15 00:21 UTC10 files · 1.45 GB

Use it

# custom terms: read the license before you download
$ fw get mlx-community/LFM2-2.6B-4bit
# manifest sha256 5eb2c8ff9e85… · 1.45 GB · 10 files
$ fw verify ./LFM2-2.6B-4bit mlx-community/LFM2-2.6B-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/LFM2-2.6B-4bit.json --dir ./LFM2-2.6B-4bit $ python3 fw.py verify ./LFM2-2.6B-4bit ./mlx-community__LFM2-2.6B-4bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/LFM2-2.6B-4bit --revision 493071ebca3592c63085e19612ded87192a2a0dd --local-dir ./LFM2-2.6B-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/LFM2-2.6B-4bit", revision="493071ebca3592c63085e19612ded87192a2a0dd") model = AutoModelForCausalLM.from_pretrained("mlx-community/LFM2-2.6B-4bit", revision="493071ebca3592c63085e19612ded87192a2a0dd", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/LFM2-2.6B-4bit --revision 493071ebca3592c63085e19612ded87192a2a0dd

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
7e170a6814f0e13f7c3f05e905e083c66c2a3e935e8be4bd5b48fb371fb2534b
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: LFM2-2.6B-4bitDate: 2026-11-15Commit: 493071eSigned: 2DC28CC7B26A283B ✓
Upstream
mlx-community/LFM2-2.6B-4bit
Pinned commit
493071ebca3592c63085e19612ded87192a2a0dd
Manifest
LFM2-2.6B-4bit.json · .minisig
Manifest sha256
5eb2c8ff9e85dc836e110c0510ca2f3a94b48edd8ade4501e76e77b0581ae2d5
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/LFM2-2.6B-4bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/LFM2-2.6B-4bit.json.minisig $ minisign -Vm LFM2-2.6B-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/LFM2-2.6B · 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/LFM2-2.6B-4bit
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. LFM2-2.6B-4bit.json. Provenance. Takedown history: none.
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