CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.qwen / Qwen3-30B-A3B-Instruct-2507-4bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.qwenSubject:

Qwen3-30B-A3B-Instruct-2507-4bit

Date: 2026-11-14Commit: e9675aaSigned: 2DC28CC7B26A283B ✓

Text generation model with 30.5B parameters. Safetensors weights, 17.2 GB in all. Published by mlx-community under Apache-2.0.

30.5B params17.2GBQwen3-30B-A3B-Instruct-2507-4bitsafetensorspermissive
FactsParams30.5BSize17.2 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit
# manifest sha256 eaead23bbb3d… · 17.2 GB · 16 files
$ fw verify ./Qwen3-30B-A3B-Instruct-2507-4bit mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit
From sourceHosted (signed)mlx-community/Qwen3-30B-A3B-Instruct-2507-4bitLast check: 2026-11-14 21:29 UTC
Run at homeGet help

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

Quantized of Qwen3-30B-A3B-Instruct-2507.

Works with

Run24Fine-tune29Convert15Evaluate13Scan13Apps58
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
17.2 GB
Weights
17.2 GB (safetensors)
Parameters
30.5B
Formats
safetensors
Task
text generation
License
Apache-2.0 (permissive)
Files
16, each with a sha256
Publisher
mlx-community
Added
2026-11-14
Section
alt.freeweights.qwen
Lineage

Original release from the publisher.

Base model: Qwen/Qwen3-30B-A3B-Instruct-2507

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.co2026-11-14 21:29 UTCpassed

Model card

From the publisher at commit e9675aa. Shown as plain text with links; images open at the publisher.

mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit#

This model mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit was converted to MLX format from Qwen/Qwen3-30B-A3B-Instruct-2507 using mlx-lm version 0.26.3.

Use with mlx#

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit")

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

16 files · 17.2 GBWeights 17.2 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 16 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md1.01 KB807bed75bf79c5da3e91010127c67338f1fccc35865115fed282635af6d88aab
added_tokens.json707 Bc0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680
chat_template.jinja4.04 KB40c21f34cf67d8c760ef72f8ad3ae5afad514299d4b06e91dd9a8d705af7b541
config.json10.9 KBe1caf81b25b71686af871f1147290a81cbcb81283b638f98957293990e031417
generation_config.json239 B19d306dd769db12a9d710b44cf7f83b635efbe5166b84fb4358a08fb7d88bb53
merges.txt1.67 MB8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
model-00001-of-00004.safetensors5.32 GB70919a0f0b7d86c3100e30dfc2c72eb29909b841f9414b9c5ae3e8673ec9ff8c
model-00002-of-00004.safetensors5.37 GB1a0387973b19b0bac1201358d1f56989deaf595da34f307ec29777fa6f8469b8
model-00003-of-00004.safetensors5.28 GBd1a627729b2791dba7db5cda5dd0d24ea4c44c5131981c258598d5d0c80e0df3
model-00004-of-00004.safetensors1.22 GBb02f0e9f626bd2f5bb41e057216c9d6f594ddeac91cc3f2161cc935d050a12c6
model.safetensors.index.json120 KBc100efb419233c6be585014ebd9f5a8c2a4fe9de63be6271172f0f70f1c315ea
special_tokens_map.json613 B76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
tokenizer.json11.4 MBaeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
tokenizer_config.json5.40 KB355f2b4e5bad7b01f11ef6cb68ebc176f61b95c3276092ea225b1bea0e01e95c
vocab.json2.78 MBca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
e9675aa3ca pinned now manifest updated, same commit2026-11-14 21:29 UTC16 files · 17.2 GB
e9675aa3ca2026-11-14 21:29 UTC16 files · 17.2 GB

Use it

$ fw get mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit
# manifest sha256 eaead23bbb3d… · 17.2 GB · 16 files
$ fw verify ./Qwen3-30B-A3B-Instruct-2507-4bit mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit.json --dir ./Qwen3-30B-A3B-Instruct-2507-4bit $ python3 fw.py verify ./Qwen3-30B-A3B-Instruct-2507-4bit ./mlx-community__Qwen3-30B-A3B-Instruct-2507-4bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit --revision e9675aa3ca5f900ccef55267914466d55ab325fa --local-dir ./Qwen3-30B-A3B-Instruct-2507-4bit
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForCausalLM, AutoTokenizer tok = AutoTokenizer.from_pretrained("mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit", revision="e9675aa3ca5f900ccef55267914466d55ab325fa") model = AutoModelForCausalLM.from_pretrained("mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit", revision="e9675aa3ca5f900ccef55267914466d55ab325fa", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit --revision e9675aa3ca5f900ccef55267914466d55ab325fa
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. 2026-11-14
Text in
README.md
Text sha256
807bed75bf79c5da3e91010127c67338f1fccc35865115fed282635af6d88aab
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: Qwen3-30B-A3B-Instruct-2507-4bitDate: 2026-11-14Commit: e9675aaSigned: 2DC28CC7B26A283B ✓
Upstream
mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit
Pinned commit
e9675aa3ca5f900ccef55267914466d55ab325fa
Manifest
Qwen3-30B-A3B-Instruct-2507-4bit.json · .minisig
Manifest sha256
eaead23bbb3d5473b6884dc7add63596b2f5674d4a6ac82f093de87453c279be
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-14 21:29 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit.json.minisig $ minisign -Vm Qwen3-30B-A3B-Instruct-2507-4bit.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/Qwen3-30B-A3B-Instruct-2507 · 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/Qwen3-30B-A3B-Instruct-2507-4bit
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. Qwen3-30B-A3B-Instruct-2507-4bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit

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