CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.text / marin-32b-base-GGUF
From: laion <huggingface.co/laion>Newsgroups: alt.freeweights.textSubject:

marin-32b-base-GGUF

Date: 2026-11-15Commit: e425040Signed: 2DC28CC7B26A283B ✓

Model. Gguf weights, 104 GB in all. Published by laion under Apache-2.0.

text104GBmarin-32b-base-GGUFggufpermissive
FactsParamsnot statedSize104 GBFormatsggufTasknot taggedLicenseApache-2.0From sourcepermissive
$ fw get laion/marin-32b-base-GGUF
# manifest sha256 363a27f10e9a… · 104 GB · 6 files
$ fw verify ./marin-32b-base-GGUF laion/marin-32b-base-GGUF
From sourceHosted (signed)laion/marin-32b-base-GGUFLast check: 2026-11-15 05:24 UTC
Run at homeGet help

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

Quantized of marin-32b-base.

Works with

Run11Convert1Scan1

Convert with

ggml

Scan with

ModelScan
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
104 GB
Weights
19.7 GB (smallest of 4 GGUF variants)
Parameters
not stated
Formats
gguf
Task
not tagged
License
Apache-2.0 (permissive)
Files
6, each with a sha256
Publisher
laion
Added
2026-11-15
Section
alt.freeweights.text
Lineage

Original release from the publisher.

Base model: marin-community/marin-32b-base

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 05:24 UTCpassed

Model card

From the publisher at commit e425040. Shown as plain text with links; images open at the publisher.

marin-32b-base-GGUF#

GGUF quantizations of marin-community/marin-32b-base, a 32B dense base model (Qwen3 architecture).

These were produced with llama.cpp (convert_hf_to_gguf.py → f16 GGUF → llama-quantize).

Available quantizations#

FileQuantNotes
marin-32b-base-Q4_K_M.ggufQ4_K_M4-bit, medium — good size/quality balance (recommended default)
marin-32b-base-Q5_K_M.ggufQ5_K_M5-bit, medium — higher quality, larger
marin-32b-base-Q6_K.ggufQ6_K6-bit — near-lossless
marin-32b-base-Q8_0.ggufQ8_08-bit — effectively lossless vs f16

Source#

  • Base model: marin-community/marin-32b-base (Apache-2.0)
  • Architecture: Qwen3 (Qwen3ForCausalLM), 64 layers, hidden 5120, vocab 128256
  • This is a base (non-instruct) model; there is no chat template.

Usage (llama.cpp)#

./llama-cli -m marin-32b-base-Q4_K_M.gguf -p "Your prompt here"

Files

6 files · 104 GBWeights 19.7 GB (smallest of 4 GGUF variants). Sizes and sha256 from the signed manifest.
Hide all 6 files with their sha256
FileSizesha256
.gitattributes1.77 KB5c9679c490c8b13752d9d9797b7b44970f1cdb7979fc8a60b5db76d254e00283
README.md1.23 KBaa1b5df8587898be9305b5f896cdd4b08f5967d53de06b49a8c6de2f91e3e9b6
marin-32b-base-Q4_K_M.gguf19.7 GB7c36374440a9f72ffc0ef4e3c75fbfe9fe3bc476cf06ed113526a55eacf7afbc
marin-32b-base-Q5_K_M.gguf23.1 GB5c19408bf4f77444d8332935296d6e8c06f937d5e763d5b4ad15efea94e046fa
marin-32b-base-Q6_K.gguf26.7 GB3d9798b2268cd234edcae2858db2c9280fa0c769580cb8a640208287dae47297
marin-32b-base-Q8_0.gguf34.6 GB10d39b5cf5f40808f0fdd0f806e248bb2c40ab46077b27172f7bacece5020e8f
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
e425040b50 pinned now2026-11-15 05:24 UTC6 files · 104 GB

Use it

$ fw get laion/marin-32b-base-GGUF
# manifest sha256 363a27f10e9a… · 104 GB · 6 files
$ fw verify ./marin-32b-base-GGUF laion/marin-32b-base-GGUF
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/laion/marin-32b-base-GGUF.json --dir ./marin-32b-base-GGUF $ python3 fw.py verify ./marin-32b-base-GGUF ./laion__marin-32b-base-GGUF.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download laion/marin-32b-base-GGUF --revision e425040b5063ba59e073f05d3c9e68bc2666b658 --local-dir ./marin-32b-base-GGUF
llama.cppDownload one GGUF variant (marin-32b-base-Q4_K_M, 19.7 GB), then serve it.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download laion/marin-32b-base-GGUF --include "marin-32b-base-Q4_K_M*" --local-dir ./marin-32b-base-GGUF $ llama-server -m ./marin-32b-base-GGUF/marin-32b-base-Q4_K_M.gguf
OllamaMake an Ollama model from the downloaded file.
$ printf 'FROM ./marin-32b-base-GGUF/marin-32b-base-Q4_K_M.gguf\n' > Modelfile $ ollama create marin-32b-base-gguf -f Modelfile
Run at home

License

Name
Apache License 2.0
Id
Apache-2.0
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
License as declared by the publisher. No person read it. 2026-11-15
Text in
README.md
Text sha256
aa1b5df8587898be9305b5f896cdd4b08f5967d53de06b49a8c6de2f91e3e9b6
Terms gate
No extra terms beyond 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: laion <huggingface.co/laion>Newsgroups: alt.freeweights.textSubject: marin-32b-base-GGUFDate: 2026-11-15Commit: e425040Signed: 2DC28CC7B26A283B ✓
Upstream
laion/marin-32b-base-GGUF
Pinned commit
e425040b5063ba59e073f05d3c9e68bc2666b658
Manifest
marin-32b-base-GGUF.json · .minisig
Manifest sha256
363a27f10e9a88101628a42ecca416f9888c2df9c18de2c4a51601664cc38ca4
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:24 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/laion/marin-32b-base-GGUF.json $ curl -O https://freeweights.allternit.com/manifests/laion/marin-32b-base-GGUF.json.minisig $ minisign -Vm marin-32b-base-GGUF.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

marin-community/marin-32b-base · this model is a quantization of it

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

Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download laion/marin-32b-base-GGUF
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. marin-32b-base-GGUF.json. Provenance. Takedown history: none.
Source
huggingface.co/laion/marin-32b-base-GGUF

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