CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.llama / Llama-3.2-3B-Instruct-4bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.llamaSubject:

Llama-3.2-3B-Instruct-4bit

Date: 2026-11-15

Text generation model with 3.2B parameters. Safetensors weights, 1.82 GB in all. Published by mlx-community under Llama-3.2-Community (custom).

3.2B params1.82GBLlama-3.2-3B-Instruct-4bitsafetensorsgated
FactsParams3.2BSize1.82 GBFormatssafetensorsTasktext generationLicenseLlama-3.2-Community (custom)From the publisher · Gatedgatedread terms
$ fw info mlx-community/Llama-3.2-3B-Instruct-4bit
link only — read the license:
https://huggingface.co/mlx-community/Llama-3.2-3B-Instruct-4bit
From the publisher · Gatedmlx-community/Llama-3.2-3B-Instruct-4bit
Get help

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

Quantized of Llama-3.2-3B-Instruct.

Works with

Run24Fine-tune29Convert15Evaluate13Scan13Apps58
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
1.82 GB
Weights
see files
Parameters
3.2B
Formats
safetensors
Task
text generation
License
Llama-3.2-Community (custom) (gated)
Files
link only
Publisher
mlx-community
Added
2026-11-15
Section
alt.freeweights.llama
Lineage

Original release from the publisher.

Base model: mlx-community/Llama-3.2-3B-Instruct

Gated at the source. The license must be accepted on the publisher's page before you download. From the publisher: downloads come from the publisher's own release. Freeweights never hosts a copy. Gated at the source: listed as a link only, and no copy is hosted. Accept the license on the model page at the source, then download from there.

Model card

No model card stored here.This model is listed with a link to the publisher. Read the publisher's page: https://huggingface.co/mlx-community/Llama-3.2-3B-Instruct-4bit

Files

Gated at the source. The license must be accepted on the publisher's page before you download. From the publisher: downloads come from the publisher's own release. Freeweights never hosts a copy. Gated at the source: listed as a link only, and no copy is hosted. Accept the license on the model page at the source, then download from there.

There is no manifest and no file list for a link-only model.

Use it

$ fw info mlx-community/Llama-3.2-3B-Instruct-4bit
link only — read the license:
https://huggingface.co/mlx-community/Llama-3.2-3B-Instruct-4bit
Gated at the source. The license must be accepted on the publisher's page before you download. From the publisher: downloads come from the publisher's own release. Freeweights never hosts a copy. Gated at the source: listed as a link only, and no copy is hosted. Accept the license on the model page at the source, then download from there.

Read the license Open the source

License

Name
Llama-3.2-Community (custom)
Id
LicenseRef-Llama-3.2-Community
Class
Gated
Redistribution
click-through
Listing
From the publisher
Decided
License as declared by the publisher. No person read it. 2026-11-15
Terms gate
Yes. The commands stay folded until you open them after reading the license.

Read the license text

Gated at the source. The license must be accepted on the publisher's page before you download. From the publisher: downloads come from the publisher's own release. Freeweights never hosts a copy. Gated at the source: listed as a link only, and no copy is hosted. Accept the license on the model page at the source, then download from there.

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.llamaSubject: Llama-3.2-3B-Instruct-4bitDate: 2026-11-15
Gated at the source. The license must be accepted on the publisher's page before you download. From the publisher: downloads come from the publisher's own release. Freeweights never hosts a copy. Gated at the source: listed as a link only, and no copy is hosted. Accept the license on the model page at the source, then download from there.
Source
huggingface.co/mlx-community/Llama-3.2-3B-Instruct-4bit
Manifest
None: Freeweights does not pin or sign link-only models.
Takedowns
None.

Model tree

Parent

mlx-community/Llama-3.2-3B-Instruct · this model is a quantization of it

No model in the catalog names this one as its parent.

Get it
License and source
Source
huggingface.co/mlx-community/Llama-3.2-3B-Instruct-4bit

Related models

All of alt.freeweights.llama →
From: BAAI <huggingface.co/BAAI>Subject: Bunny-Llama-3-8B-V
From: BAAI <huggingface.co/BAAI>Subject: Bunny-Llama-3-8B-V-gguf
From: BAAI <huggingface.co/BAAI>Subject: Bunny-v1_1-Llama-3-8B-V
From: unsloth <huggingface.co/unsloth>Subject: codellama-7b
From: unsloth <huggingface.co/unsloth>Subject: codellama-7b-bnb-4bit
From: BAAI <huggingface.co/BAAI>Subject: Infinity-Instruct-3M-0613-Llama3-70B