CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.qwen / Qwen3-Next-80B-A3B-Thinking-4bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.qwenSubject:

Qwen3-Next-80B-A3B-Thinking-4bit

Date: 2026-11-15Commit: 9a2b463Signed: 2DC28CC7B26A283B ✓

Text generation model with 79.7B parameters. Safetensors weights, 44.9 GB in all. Published by mlx-community under Apache-2.0.

79.7B params44.9GBQwen3-Next-80B-A3B-Thinking-4bitsafetensorspermissive
FactsParams79.7BSize44.9 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/Qwen3-Next-80B-A3B-Thinking-4bit
# manifest sha256 35aba60a8943… · 44.9 GB · 21 files
$ fw verify ./Qwen3-Next-80B-A3B-Thinking-4bit mlx-community/Qwen3-Next-80B-A3B-Thinking-4bit
From sourceHosted (signed)mlx-community/Qwen3-Next-80B-A3B-Thinking-4bitLast check: 2026-11-15 05:12 UTC
Run at homeGet help

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

Quantized of Qwen3-Next-80B-A3B-Thinking.

Works with

Run24Fine-tune29Convert15Evaluate13Scan13Apps58
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
44.9 GB
Weights
44.8 GB (safetensors)
Parameters
79.7B
Formats
safetensors
Task
text generation
License
Apache-2.0 (permissive)
Files
21, 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-Next-80B-A3B-Thinking

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 05:12 UTCpassed

Model card

From the publisher at commit 9a2b463. Shown as plain text with links; images open at the publisher.

mlx-community/Qwen3-Next-80B-A3B-Thinking-4bit#

This model mlx-community/Qwen3-Next-80B-A3B-Thinking-4bit was converted to MLX format from Qwen/Qwen3-Next-80B-A3B-Thinking using mlx-lm version 0.27.1.

Use with mlx#

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Qwen3-Next-80B-A3B-Thinking-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

21 files · 44.9 GBWeights 44.8 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 21 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md1.01 KB3be77799385763296b2b10a11410ef7c29b113646456188a9201ebac970cf23b
added_tokens.json707 Bc0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680
chat_template.jinja4.05 KB3802169b2a02b81e6adb7ab4f64f91ff02db753c8c3a64a01c35192d3a61d8d7
config.json22.1 KBf5a5422b8e3d47733f0073ff22dec1dc4a7832fec5fc1cf36eba31ace03cf0c4
generation_config.json222 B977b508fb0699135726dfbd927b9114ae55e5a404541bf53f8fb3fe6c173c6ca
merges.txt1.67 MB8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
model-00001-of-00009.safetensors5.13 GBcf2a38d6c9911289ea547fcab937751a96eec25c4ccf0bf3289c55bed8c70d90
model-00002-of-00009.safetensors5.26 GBfa14e30824fd7e6a3b2d0987c60ebfcc42fafe2c54db9ef96f4b860dd834f3d4
model-00003-of-00009.safetensors5.24 GBff40996f09bbe74591555b8768bdc739cea89e763031300127c56656d2cb0590
model-00004-of-00009.safetensors5.26 GB8280cc0e1f6b8cc972b03a88a120e8df62e0a02890cf68f8099617d78653cfe8
model-00005-of-00009.safetensors5.26 GBaa4394a09de3e73a1837416233a004af6ca7e215e26f0fed63e7e4701207121e
model-00006-of-00009.safetensors5.24 GB2c8f53a4a68ff9239a8ad5d5e286271ccc2702bdf513864decc49fc1599bf520
model-00007-of-00009.safetensors5.26 GB696e577c09c6f67096b5fe7ae60440ee5fe7fd210c2a23f73843fe610ce89543
model-00008-of-00009.safetensors5.26 GBf92a3c03459b057d76ba3c2fd71f4c587b6203cdf026ed554537c27ee68abe4c
model-00009-of-00009.safetensors2.93 GB09d1eeea5959f6f555328df67685c0c0f2c64dae03a4c909bb367e96c22bb873
model.safetensors.index.json173 KB4ab1fbfbc6e42a84c6b810745765db249350ab1df1d1cdb0c2841de89e8ca309
special_tokens_map.json613 B76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
tokenizer.json11.4 MBaeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
tokenizer_config.json5.41 KB4b5f2f80f84faefe8420e1616671adb1dd3d7e632038d34b1f0e3a1363a51059
vocab.json2.78 MBca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
9a2b46347b pinned now2026-11-15 05:12 UTC21 files · 44.9 GB

Use it

$ fw get mlx-community/Qwen3-Next-80B-A3B-Thinking-4bit
# manifest sha256 35aba60a8943… · 44.9 GB · 21 files
$ fw verify ./Qwen3-Next-80B-A3B-Thinking-4bit mlx-community/Qwen3-Next-80B-A3B-Thinking-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-Next-80B-A3B-Thinking-4bit.json --dir ./Qwen3-Next-80B-A3B-Thinking-4bit $ python3 fw.py verify ./Qwen3-Next-80B-A3B-Thinking-4bit ./mlx-community__Qwen3-Next-80B-A3B-Thinking-4bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Qwen3-Next-80B-A3B-Thinking-4bit --revision 9a2b46347bb170cb2924092175fa21554fe585a9 --local-dir ./Qwen3-Next-80B-A3B-Thinking-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-Next-80B-A3B-Thinking-4bit", revision="9a2b46347bb170cb2924092175fa21554fe585a9") model = AutoModelForCausalLM.from_pretrained("mlx-community/Qwen3-Next-80B-A3B-Thinking-4bit", revision="9a2b46347bb170cb2924092175fa21554fe585a9", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/Qwen3-Next-80B-A3B-Thinking-4bit --revision 9a2b46347bb170cb2924092175fa21554fe585a9
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
3be77799385763296b2b10a11410ef7c29b113646456188a9201ebac970cf23b
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-Next-80B-A3B-Thinking-4bitDate: 2026-11-15Commit: 9a2b463Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/Qwen3-Next-80B-A3B-Thinking-4bit
Pinned commit
9a2b46347bb170cb2924092175fa21554fe585a9
Manifest
Qwen3-Next-80B-A3B-Thinking-4bit.json · .minisig
Manifest sha256
35aba60a89439bf6281150dd55236531667901233033be0a467ae021c7d1cb52
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:12 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3-Next-80B-A3B-Thinking-4bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3-Next-80B-A3B-Thinking-4bit.json.minisig $ minisign -Vm Qwen3-Next-80B-A3B-Thinking-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-Next-80B-A3B-Thinking · 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-Next-80B-A3B-Thinking-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-Next-80B-A3B-Thinking-4bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/Qwen3-Next-80B-A3B-Thinking-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