CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.olmo / Olmo-3.1-32B-Think-8bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.olmoSubject:

Olmo-3.1-32B-Think-8bit

Date: 2026-11-15Commit: 306e81dSigned: 2DC28CC7B26A283B ✓

Text generation model with 32.2B parameters. Safetensors weights, 34.3 GB in all. Published by mlx-community under Apache-2.0.

32.2B params34.3GBOlmo-3.1-32B-Think-8bitsafetensorspermissive
FactsParams32.2BSize34.3 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/Olmo-3.1-32B-Think-8bit
# manifest sha256 1a02585f1d70… · 34.3 GB · 15 files
$ fw verify ./Olmo-3.1-32B-Think-8bit mlx-community/Olmo-3.1-32B-Think-8bit
From sourceHosted (signed)mlx-community/Olmo-3.1-32B-Think-8bitLast check: 2026-11-15 05:16 UTC
Run at homeGet help

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

Quantized of Olmo-3.1-32B-Think.

Works with

Run24Fine-tune29Convert15Evaluate13Scan13Apps58
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
34.3 GB
Weights
34.2 GB (safetensors)
Parameters
32.2B
Formats
safetensors
Task
text generation
License
Apache-2.0 (permissive)
Files
15, each with a sha256
Publisher
mlx-community
Added
2026-11-15
Section
alt.freeweights.olmo
Lineage

Original release from the publisher.

Base model: allenai/Olmo-3.1-32B-Think

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 05:16 UTCpassed

Model card

From the publisher at commit 306e81d. Shown as plain text with links; images open at the publisher.

mlx-community/Olmo-3.1-32B-Think-8bit#

This model mlx-community/Olmo-3.1-32B-Think-8bit was converted to MLX format from allenai/Olmo-3.1-32B-Think using mlx-lm version 0.29.2.

Use with mlx#

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Olmo-3.1-32B-Think-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, return_dict=False,
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)

Files

15 files · 34.3 GBWeights 34.2 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 15 files with their sha256
FileSizesha256
.gitattributes1.52 KB11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361
README.md937 B09559d13f6939d6560df96891e5ecf2a1fd13dcd132352faafa86291817a6c4c
chat_template.jinja1.56 KBfb2b8736121ab4001112a9ccfb33c0081230536c861c706bf24b1b390964c1cd
config.json2.94 KBada6a95febc3539cd17bd7fb274c72e0f8565524efab0174c466eb63613b63c4
generation_config.json207 B9ca20766a58daf4a6e1bf5f6552d27dbe57733dba2c3af507dd9f4b12aacc0b0
model-00001-of-00007.safetensors5.28 GB8e4a5d0002898b191ae9ee38384c241e646465a23c44923b9567c6e11d53ed3e
model-00002-of-00007.safetensors5.33 GB76d7f289abf0ce39d247ada343f78534adf3e668561f60864a9e8fbf59128fac
model-00003-of-00007.safetensors5.33 GBe2bc9ec18eadc9589d548555f0ffc789e987c2ad0ec51eeb23efe898c1c9b71b
model-00004-of-00007.safetensors5.36 GB9006dad1246c24b13a5a45aeed96c2f1827a68434a08647251370d10c0906975
model-00005-of-00007.safetensors5.36 GBa3d19953ce5ac3de6c89c11bb3700597c8a33db378df00c5a7e0a94f33fa319b
model-00006-of-00007.safetensors5.33 GBc4a9675067fdbfe1125ca517d4c99475da72238d3c3dd4281c325f4ad41ea21b
model-00007-of-00007.safetensors2.25 GBc261f63003f8523356a39cffbfe3c695200b398c7cac357fe6dd4f66c5438fbf
model.safetensors.index.json139 KB84f9f7573d4afe2cfa7c4f0468d8f52bd043a03e5b4ba30fb325b5b90f6b9753
tokenizer.json7.14 MB18e309ad7f9c60037eaf26aca401a96128187cad2bdfa01a508dca7526bf6300
tokenizer_config.json434 B749bd7083f47e63ddc131fdbc447abee264c070d9d8b66eb669215413775d7a3
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
306e81d6b0 pinned now2026-11-15 05:16 UTC15 files · 34.3 GB

Use it

$ fw get mlx-community/Olmo-3.1-32B-Think-8bit
# manifest sha256 1a02585f1d70… · 34.3 GB · 15 files
$ fw verify ./Olmo-3.1-32B-Think-8bit mlx-community/Olmo-3.1-32B-Think-8bit
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/Olmo-3.1-32B-Think-8bit.json --dir ./Olmo-3.1-32B-Think-8bit $ python3 fw.py verify ./Olmo-3.1-32B-Think-8bit ./mlx-community__Olmo-3.1-32B-Think-8bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Olmo-3.1-32B-Think-8bit --revision 306e81d6b03e9b58b1cef88a2bff5ed6b6c27442 --local-dir ./Olmo-3.1-32B-Think-8bit
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/Olmo-3.1-32B-Think-8bit", revision="306e81d6b03e9b58b1cef88a2bff5ed6b6c27442") model = AutoModelForCausalLM.from_pretrained("mlx-community/Olmo-3.1-32B-Think-8bit", revision="306e81d6b03e9b58b1cef88a2bff5ed6b6c27442", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/Olmo-3.1-32B-Think-8bit --revision 306e81d6b03e9b58b1cef88a2bff5ed6b6c27442
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
09559d13f6939d6560df96891e5ecf2a1fd13dcd132352faafa86291817a6c4c
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: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.olmoSubject: Olmo-3.1-32B-Think-8bitDate: 2026-11-15Commit: 306e81dSigned: 2DC28CC7B26A283B ✓
Upstream
mlx-community/Olmo-3.1-32B-Think-8bit
Pinned commit
306e81d6b03e9b58b1cef88a2bff5ed6b6c27442
Manifest
Olmo-3.1-32B-Think-8bit.json · .minisig
Manifest sha256
1a02585f1d70401dc336184e670952fb2448b75302305142263511714c62e7fc
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:16 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Olmo-3.1-32B-Think-8bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/Olmo-3.1-32B-Think-8bit.json.minisig $ minisign -Vm Olmo-3.1-32B-Think-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

Parent

allenai/Olmo-3.1-32B-Think · 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 mlx-community/Olmo-3.1-32B-Think-8bit
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. Olmo-3.1-32B-Think-8bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/Olmo-3.1-32B-Think-8bit

Related models

All of alt.freeweights.olmo →
From: bartowski <huggingface.co/bartowski>Subject: allenai_Olmo-3-7B-Instruct-GGUF
From: bartowski <huggingface.co/bartowski>Subject: allenai_Olmo-3-7B-Think-GGUF
From: bartowski <huggingface.co/bartowski>Subject: allenai_Olmo-3.1-32B-Instruct-GGUF
From: bartowski <huggingface.co/bartowski>Subject: allenai_Olmo-3.1-32B-Think-GGUF
From: bartowski <huggingface.co/bartowski>Subject: allenai_olmOCR-2-7B-1025-GGUF
From: bartowski <huggingface.co/bartowski>Subject: allenai_olmOCR-7B-0225-preview-GGUF