From: <huggingface.co/mlx-community> Newsgroups: alt.freeweights.lfmSubject: LFM2-350M-8bit Date: 2026-11-15Commit: 3b5014aSigned: 2DC28CC7B26A283B ✓ Text generation model with 354M parameters. Safetensors weights, 382 MB in all. Published by mlx-community under LFM-1.0 (custom).
354M params 382 MB LFM2-350M-8bit safetensors custom terms Facts Params 354M Size 382 MB Formats safetensors Task text generation License LFM-1.0 (custom) custom terms read terms
fw
# custom terms: read the license before you download
$ fw get mlx-community/LFM2-350M-8bit
# manifest sha256 85bef03fe8d3… · 382 MB · 10 files
$ fw verify ./LFM2-350M-8bit mlx-community/LFM2-350M-8bitHosted (signed) mlx-community/LFM2-350M-8bit Last check: 2026-11-15 00:21 UTC
Get help: custom fine-tune or private deploy. We review your setup before we quote.
Quantized of LFM2-350M .
Works with
Runs with Ranked by fit to this model (safetensors), then by GitHub stars.
Show all 24 Fine-tune with Show all 29
Overview
Size 382 MB
Weights 377 MB (safetensors)
Parameters 354M
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/LFM2-350M
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 huggingface.co 2026-11-15 00:21 UTC passed
Model card From the publisher at commit
3b5014a . Shown as plain text with links; images open at the publisher.
This model mlx-community/LFM2-350M-8bit was converted to MLX format from LiquidAI/LFM2-350M using mlx-lm version 0.26.0 .
Use with mlx#
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/LFM2-350M-8bit")
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 · 382 MB Weights 377 MB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 10 files with their sha256 File Size sha256 .gitattributes 1.52 KB 11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361 README.md 918 B e44409937d39521ac91bd80f1ff23bbd0b982bb29f219cb200b4eb4d1d3db125 chat_template.jinja 209 B a805e50fed68938a076b07e2e602639611b50b1ced0e50f11eb92f1ba25be4dc config.json 1.25 KB 1399051f414dacc96f6fad575d49941151f743b8eacdef89d8e1195384b97a62 generation_config.json 137 B 0f678f07a00ae4bdeb2b2bd5f37988a4b33a87686d9103fefe08de7a46522373 model.safetensors 377 MB a9b52fefdc6f8986568385c422348fce1f1cfb7c91085b1861b1ee94610a4449 model.safetensors.index.json 23.4 KB 5bba814effdd10fdaad704b33f7ba929396e46422c8c0c55156f588cee4c6ffd special_tokens_map.json 434 B 742aefe2b7dec496e8caffdba03a75d0c1a9925d53bd3f3e0d388c96b591b6f4 tokenizer.json 4.73 MB 98cff83b4f6d7e9d8929bebc62b07e92cf1b3f99c80d16bafe8b84a75448f40b tokenizer_config.json 91.5 KB 36f511115e9d8952cbc9d15d9a20dfa7ce7d1444940e5c1dc42a762020c99bf5
Versions Each time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commit Date Contents 3b5014a196 pinned now 2026-11-15 00:21 UTC 10 files · 382 MB
Use it fw
# custom terms: read the license before you download
$ fw get mlx-community/LFM2-350M-8bit
# manifest sha256 85bef03fe8d3… · 382 MB · 10 files
$ fw verify ./LFM2-350M-8bit mlx-community/LFM2-350M-8bitTerms 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.py Checks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/LFM2-350M-8bit.json --dir ./LFM2-350M-8bit
$ python3 fw.py verify ./LFM2-350M-8bit ./mlx-community__LFM2-350M-8bit.jsonhf The Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT =https://freeweights.allternit.com hf download mlx-community/LFM2-350M-8bit --revision 3b5014a1966c54313045fd0a23a098a220083b1e --local-dir ./LFM2-350M-8bittransformers Load 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/LFM2-350M-8bit", revision="3b5014a1966c54313045fd0a23a098a220083b1e")
model = AutoModelForCausalLM.from_pretrained("mlx-community/LFM2-350M-8bit", revision="3b5014a1966c54313045fd0a23a098a220083b1e", device_map="auto")vLLM Serve an OpenAI-compatible API.
$ HF_ENDPOINT =https://freeweights.allternit.com vllm serve mlx-community/LFM2-350M-8bit --revision 3b5014a1966c54313045fd0a23a098a220083b1eLicense 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 e44409937d39521ac91bd80f1ff23bbd0b982bb29f219cb200b4eb4d1d3db125 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: <huggingface.co/mlx-community> Newsgroups: alt.freeweights.lfmSubject: LFM2-350M-8bit Date: 2026-11-15Commit: 3b5014aSigned: 2DC28CC7B26A283B ✓ Upstream mlx-community/LFM2-350M-8bit Pinned commit 3b5014a1966c54313045fd0a23a098a220083b1e Manifest LFM2-350M-8bit.json · .minisig Manifest sha256 85bef03fe8d365cbba39f1cb58318bc41df7d15c43d055f25cdb88edb57b1bfc 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/LFM2-350M-8bit.json
$ curl -O https://freeweights.allternit.com/manifests/mlx-community/LFM2-350M-8bit.json.minisig
$ minisign -Vm LFM2-350M-8bit.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 model in the catalog names this one as its parent.
1.2B params 2.35 GB LFM2-1.2B safetensors custom terms Facts Params 1.2B Size 2.35 GB Formats safetensors Task text generation License LFM-1.0 (custom) custom terms read terms flip From: LiquidAI <huggingface.co/LiquidAI> Subject: LFM2-1.2B 1.2B params 2.35 GB LFM2-1.2B-Extract safetensors custom terms Facts Params 1.2B Size 2.35 GB Formats safetensors Task text generation License LFM-1.0 (custom) custom terms read terms flip From: LiquidAI <huggingface.co/LiquidAI> Subject: LFM2-1.2B-Extract 1.2B params 2.35 GB LFM2-1.2B-RAG safetensors custom terms Facts Params 1.2B Size 2.35 GB Formats safetensors Task text generation License LFM-1.0 (custom) custom terms read terms flip From: LiquidAI <huggingface.co/LiquidAI> Subject: LFM2-1.2B-RAG 1.2B params 2.35 GB LFM2-1.2B-Tool safetensors custom terms Facts Params 1.2B Size 2.35 GB Formats safetensors Task text generation License LFM-1.0 (custom) custom terms read terms flip From: LiquidAI <huggingface.co/LiquidAI> Subject: LFM2-1.2B-Tool 2.6B params 5.14 GB LFM2-2.6B safetensors custom terms Facts Params 2.6B Size 5.14 GB Formats safetensors Task text generation License LFM-1.0 (custom) custom terms read terms flip From: LiquidAI <huggingface.co/LiquidAI> Subject: LFM2-2.6B 2.6B params 5.14 GB LFM2-2.6B-Exp safetensors custom terms Facts Params 2.6B Size 5.14 GB Formats safetensors Task text generation License LFM-1.0 (custom) custom terms read terms flip From: LiquidAI <huggingface.co/LiquidAI> Subject: LFM2-2.6B-Exp
mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.lfmSubject: 
