CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.qwen / Qwen3-32B-8bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.qwenSubject:

Qwen3-32B-8bit

Date: 2026-11-15Commit: 916c25bSigned: 2DC28CC7B26A283B ✓

Text generation model with 32.8B parameters. Safetensors weights, 34.8 GB in all. Published by mlx-community under Apache-2.0.

32.8B params34.8GBQwen3-32B-8bitsafetensorspermissive
FactsParams32.8BSize34.8 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/Qwen3-32B-8bit
# manifest sha256 fffd8baf11c9… · 34.8 GB · 17 files
$ fw verify ./Qwen3-32B-8bit mlx-community/Qwen3-32B-8bit
From sourceHosted (signed)mlx-community/Qwen3-32B-8bitLast check: 2026-11-15 05:17 UTC
Run at homeGet help

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

Quantized of Qwen3-32B.

Works with

Run24Fine-tune29Convert15Evaluate13Scan13Apps58
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
34.8 GB
Weights
34.8 GB (safetensors)
Parameters
32.8B
Formats
safetensors
Task
text generation
License
Apache-2.0 (permissive)
Files
17, each with a sha256
Publisher
mlx-community
Added
2026-11-15
Section
alt.freeweights.qwen
Lineage

Original release from the publisher.

Base model: Qwen/Qwen3-32B

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 05:17 UTCpassed

Model card

From the publisher at commit 916c25b. Shown as plain text with links; images open at the publisher.

mlx-community/Qwen3-32B-8bit#

This model mlx-community/Qwen3-32B-8bit was converted to MLX format from Qwen/Qwen3-32B using mlx-lm version 0.24.0.

Use with mlx#

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Qwen3-32B-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

17 files · 34.8 GBWeights 34.8 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 17 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md865 Bceb50f44a49d21f7fd274f27fe3a10ffd12ebf90e1036c64e083dc489ba09546
added_tokens.json707 Bc0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680
config.json939 Bfef38fb57fab21370a6711ae5275dbb84f603f9dd6eff18b625f8eca830cfbca
merges.txt1.67 MB8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
model-00001-of-00007.safetensors5.35 GBa44678157629ed64d26ee3c7c7b3ad9faca59de5663191bc34b50a5e48d67c03
model-00002-of-00007.safetensors5.36 GB20b0b445f3bbd64dbca78b5776289ecc4ecdc62067f1dd7d39bf299be016f235
model-00003-of-00007.safetensors5.37 GBa121946d454ca6f28449855bd3fdd1f16a8cbf26497d886d06f48c1404b6aff4
model-00004-of-00007.safetensors5.33 GB57478686da78436ae03337e8ecfbea79154c11f77d1c36e4dc302b90fe52f475
model-00005-of-00007.safetensors5.36 GBbbef062cc29879051f2630e5484e27c489d40e35cc52f73ae07d2fc91e73de04
model-00006-of-00007.safetensors5.37 GBb3fc3cd8b97ff1fc2d3eff74c7c67a3a2e51feeeb0bfb72a6cbab14372aef7f4
model-00007-of-00007.safetensors2.67 GB43b9572762e64ab663b5cf0916dfebadfdceb4ce61d8d23744755c51d1b799ca
model.safetensors.index.json138 KB2ea44ef1f37994fa62b3844770c5c7ae36e105295a15e8c54d4e4876826ccba1
special_tokens_map.json613 B76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
tokenizer.json11.4 MBaeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
tokenizer_config.json9.71 KB253153d0738ceb4c668d2eff957714dd2bea0b56de772a9fdccd96cbf517e6a0
vocab.json2.78 MBca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
916c25b033 pinned now2026-11-15 05:17 UTC17 files · 34.8 GB

Use it

$ fw get mlx-community/Qwen3-32B-8bit
# manifest sha256 fffd8baf11c9… · 34.8 GB · 17 files
$ fw verify ./Qwen3-32B-8bit mlx-community/Qwen3-32B-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/Qwen3-32B-8bit.json --dir ./Qwen3-32B-8bit $ python3 fw.py verify ./Qwen3-32B-8bit ./mlx-community__Qwen3-32B-8bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Qwen3-32B-8bit --revision 916c25b033bc96694567ad50c60ab4759a21bad2 --local-dir ./Qwen3-32B-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/Qwen3-32B-8bit", revision="916c25b033bc96694567ad50c60ab4759a21bad2") model = AutoModelForCausalLM.from_pretrained("mlx-community/Qwen3-32B-8bit", revision="916c25b033bc96694567ad50c60ab4759a21bad2", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/Qwen3-32B-8bit --revision 916c25b033bc96694567ad50c60ab4759a21bad2
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
ceb50f44a49d21f7fd274f27fe3a10ffd12ebf90e1036c64e083dc489ba09546
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.qwenSubject: Qwen3-32B-8bitDate: 2026-11-15Commit: 916c25bSigned: 2DC28CC7B26A283B ✓
Upstream
mlx-community/Qwen3-32B-8bit
Pinned commit
916c25b033bc96694567ad50c60ab4759a21bad2
Manifest
Qwen3-32B-8bit.json · .minisig
Manifest sha256
fffd8baf11c93069e339418a38104c72d9df080ca4616ab3943d7dbdafca95de
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:17 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3-32B-8bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3-32B-8bit.json.minisig $ minisign -Vm Qwen3-32B-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

Qwen/Qwen3-32B · 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/Qwen3-32B-8bit
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. Qwen3-32B-8bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/Qwen3-32B-8bit

Related models

All of alt.freeweights.qwen →
From: BAAI <huggingface.co/BAAI>Subject: Aquila-VL-2B-llava-qwen
From: Perciqa <huggingface.co/Perciqa>Subject: Aurora-Code-1
From: BAAI <huggingface.co/BAAI>Subject: bge-reasoner-embed-qwen3-8b-0923
From: amazon <huggingface.co/amazon>Subject: BMOJOF-primed-HQwen3-8B-Instruct
From: nbeerbower <huggingface.co/nbeerbower>Subject: Bubba-Qwen3.6-27B-LoRA
From: bartowski <huggingface.co/bartowski>Subject: bytkim_Qwen3.8-27B-pi-GGUF