CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.text / KernelLLM
From: facebook <huggingface.co/facebook>Newsgroups: alt.freeweights.textSubject:

KernelLLM

Date: 2026-11-15

Text generation model with 8B parameters. Safetensors weights, 16.1 GB in all. Published by facebook under Llama-3.1-Community (custom).

8B params16.1GBKernelLLMsafetensorsgated
FactsParams8BSize16.1 GBFormatssafetensorsTasktext generationLicenseLlama-3.1-Community (custom)From the publisher · Gatedgatedread terms
$ fw info facebook/KernelLLM
link only — read the license:
https://huggingface.co/facebook/KernelLLM/blob/26d1191a7186ac499448a868a2ecdf9ef8d3abd5/LICENSE.pdf
From the publisher · Gatedfacebook/KernelLLM
Get 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
16.1 GB
Weights
see files
Parameters
8B
Formats
safetensors
Task
text generation
License
Llama-3.1-Community (custom) (gated)
Files
link only
Publisher
facebook
Added
2026-11-15
Section
alt.freeweights.text
Lineage

Original release from the publisher.

Base model: meta-llama/Llama-3.1-8B-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. The license of the base model meta-llama/Llama-3.1-8B-Instruct applies: the strictest license along the lineage wins.

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/facebook/KernelLLM

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. The license of the base model meta-llama/Llama-3.1-8B-Instruct applies: the strictest license along the lineage wins.

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

Use it

$ fw info facebook/KernelLLM
link only — read the license:
https://huggingface.co/facebook/KernelLLM/blob/26d1191a7186ac499448a868a2ecdf9ef8d3abd5/LICENSE.pdf
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. The license of the base model meta-llama/Llama-3.1-8B-Instruct applies: the strictest license along the lineage wins.

Read the license Open the source

License

Name
Llama-3.1-Community (custom)
Id
LicenseRef-Llama-3.1-Community
Class
Gated
Redistribution
click-through
Listing
From the publisher
Decided
Inherited from the base model meta-llama/Llama-3.1-8B-Instruct: the strictest license along the lineage applies. 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. The license of the base model meta-llama/Llama-3.1-8B-Instruct applies: the strictest license along the lineage wins.

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From: facebook <huggingface.co/facebook>Newsgroups: alt.freeweights.textSubject: KernelLLMDate: 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. The license of the base model meta-llama/Llama-3.1-8B-Instruct applies: the strictest license along the lineage wins.
Source
huggingface.co/facebook/KernelLLM
Manifest
None: Freeweights does not pin or sign link-only models.
Takedowns
None.

Model tree

Parent

meta-llama/Llama-3.1-8B-Instruct (not in this catalog) · this model is a finetune of it

3 models in the catalog name this one as their parent.

Quantizations
3
Quantizations 3
Get it
License and source
Source
huggingface.co/facebook/KernelLLM

Variants

3 quantized or adapter builds of KernelLLM. Each has its own license check and page.

SubjectSizeParamsLicenseDate
KernelLLM-GGUFFrom the publisher From: unsloth in alt.freeweights.text130 GB—Gated2026-11-15facebook_KernelLLM-GGUFFrom the publisher From: bartowski in alt.freeweights.text126 GB—Gated2026-11-15KernelLLM-GGUFFrom the publisher From: lmstudio-community in alt.freeweights.text24.4 GB—Gated2026-11-15

Related models

All of alt.freeweights.text →
From: laion <huggingface.co/laion>Subject: a2-rl-e2egit_large-50-32B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_e2egit-large-15-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_e2egit-v2-10-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_pymethods2test-large-80-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_exp_rpt_unitsyn-python-large-10-8B
From: laion <huggingface.co/laion>Subject: a3-rl-DCAgent_mix_h2_language_proportional-65-8B