CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.qwen / Qwen3-32B-MLX-4bit
From: lmstudio-community <huggingface.co/lmstudio-community>Newsgroups: alt.freeweights.qwenSubject:

Qwen3-32B-MLX-4bit

Date: 2026-11-15Commit: b373dfdSigned: 2DC28CC7B26A283B ✓

Text generation model with 32.8B parameters. Safetensors weights, 18.4 GB in all. Published by lmstudio-community under Apache-2.0.

32.8B params18.4GBQwen3-32B-MLX-4bitsafetensorspermissive
FactsParams32.8BSize18.4 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get lmstudio-community/Qwen3-32B-MLX-4bit
# manifest sha256 e53c339a5962… · 18.4 GB · 14 files
$ fw verify ./Qwen3-32B-MLX-4bit lmstudio-community/Qwen3-32B-MLX-4bit
From sourceHosted (signed)lmstudio-community/Qwen3-32B-MLX-4bitLast check: 2026-11-15 04:47 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
18.4 GB
Weights
18.4 GB (safetensors)
Parameters
32.8B
Formats
safetensors
Task
text generation
License
Apache-2.0 (permissive)
Files
14, each with a sha256
Publisher
lmstudio-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 04:47 UTCpassed

Model card

From the publisher at commit b373dfd. Shown as plain text with links; images open at the publisher.

lmstudio-community/Qwen3-32B-MLX-4bit#

This model lmstudio-community/Qwen3-32B-MLX-4bit 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("lmstudio-community/Qwen3-32B-MLX-4bit")

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

14 files · 18.4 GBWeights 18.4 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 14 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md900 Be932e4c89e2c35a5c480553f1142026ec176315eccef0eb8c76e48a47cecdf99
added_tokens.json707 Bc0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680
config.json939 B61164e05c52435ed08ee11d4ead8833577f7d329d05797fde522f457b80c25dd
merges.txt1.67 MB8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
model-00001-of-00004.safetensors5.37 GBc37d8ac8663e5bcfb7334889dcba56e3c6b3d7a9b8643a62c5f8b6105765aee1
model-00002-of-00004.safetensors5.35 GB2f8fbccad32a2a2f3072ffb8d6adea2790cc0bd84927cc0c44fbaf1d97912867
model-00003-of-00004.safetensors5.36 GB4412f7fa42e1419455698d3fe2b3c9557badd36a8a5c3a8d3d2439fc2fa6f0de
model-00004-of-00004.safetensors2.36 GB5cdadd1a77ec47b3ea7799255efb7d15431765874963f55a33f71f43386eb619
model.safetensors.index.json138 KBdbe52fe0c696b83058e0ba1458d202105135ae33c602464bde2b406323498fd3
special_tokens_map.json613 B76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
tokenizer.json11.4 MBaeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
tokenizer_config.json10.2 KB8e7dd4250db58b2a29792562d727b2715dc0fe79a94b446caa4c07db39eceba6
vocab.json2.78 MBca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
b373dfda08 pinned now2026-11-15 04:47 UTC14 files · 18.4 GB

Use it

$ fw get lmstudio-community/Qwen3-32B-MLX-4bit
# manifest sha256 e53c339a5962… · 18.4 GB · 14 files
$ fw verify ./Qwen3-32B-MLX-4bit lmstudio-community/Qwen3-32B-MLX-4bit
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/lmstudio-community/Qwen3-32B-MLX-4bit.json --dir ./Qwen3-32B-MLX-4bit $ python3 fw.py verify ./Qwen3-32B-MLX-4bit ./lmstudio-community__Qwen3-32B-MLX-4bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download lmstudio-community/Qwen3-32B-MLX-4bit --revision b373dfda08db5ac018dac5ac86a93bc32fa90feb --local-dir ./Qwen3-32B-MLX-4bit
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForCausalLM, AutoTokenizer tok = AutoTokenizer.from_pretrained("lmstudio-community/Qwen3-32B-MLX-4bit", revision="b373dfda08db5ac018dac5ac86a93bc32fa90feb") model = AutoModelForCausalLM.from_pretrained("lmstudio-community/Qwen3-32B-MLX-4bit", revision="b373dfda08db5ac018dac5ac86a93bc32fa90feb", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve lmstudio-community/Qwen3-32B-MLX-4bit --revision b373dfda08db5ac018dac5ac86a93bc32fa90feb
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
e932e4c89e2c35a5c480553f1142026ec176315eccef0eb8c76e48a47cecdf99
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: lmstudio-community <huggingface.co/lmstudio-community>Newsgroups: alt.freeweights.qwenSubject: Qwen3-32B-MLX-4bitDate: 2026-11-15Commit: b373dfdSigned: 2DC28CC7B26A283B ✓
Upstream
lmstudio-community/Qwen3-32B-MLX-4bit
Pinned commit
b373dfda08db5ac018dac5ac86a93bc32fa90feb
Manifest
Qwen3-32B-MLX-4bit.json · .minisig
Manifest sha256
e53c339a5962ae6250e9b6772e43284d5c2f46ea40f707e97028d862ee056e78
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 04:47 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/lmstudio-community/Qwen3-32B-MLX-4bit.json $ curl -O https://freeweights.allternit.com/manifests/lmstudio-community/Qwen3-32B-MLX-4bit.json.minisig $ minisign -Vm Qwen3-32B-MLX-4bit.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 lmstudio-community/Qwen3-32B-MLX-4bit
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-MLX-4bit.json. Provenance. Takedown history: none.
Source
huggingface.co/lmstudio-community/Qwen3-32B-MLX-4bit

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