CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.qwen / Qwen3-Next-80B-A3B-Instruct-8bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.qwenSubject:

Qwen3-Next-80B-A3B-Instruct-8bit

Date: 2026-11-15Commit: fd52af0Signed: 2DC28CC7B26A283B ✓

Text generation model with 79.7B parameters. Safetensors weights, 84.7 GB in all. Published by mlx-community under Apache-2.0.

79.7B params84.7GBQwen3-Next-80B-A3B-Instruct-8bitsafetensorspermissive
FactsParams79.7BSize84.7 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/Qwen3-Next-80B-A3B-Instruct-8bit
# manifest sha256 b1a0aac47458… · 84.7 GB · 29 files
$ fw verify ./Qwen3-Next-80B-A3B-Instruct-8bit mlx-community/Qwen3-Next-80B-A3B-Instruct-8bit
From sourceHosted (signed)mlx-community/Qwen3-Next-80B-A3B-Instruct-8bitLast check: 2026-11-15 05:12 UTC
Get help

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

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

Works with

Run24Fine-tune29Convert15Evaluate13Scan13Apps58
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
84.7 GB
Weights
84.7 GB (safetensors)
Parameters
79.7B
Formats
safetensors
Task
text generation
License
Apache-2.0 (permissive)
Files
29, 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-Instruct

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 fd52af0. Shown as plain text with links; images open at the publisher.

mlx-community/Qwen3-Next-80B-A3B-Instruct-8bit#

This model mlx-community/Qwen3-Next-80B-A3B-Instruct-8bit was converted to MLX format from Qwen/Qwen3-Next-80B-A3B-Instruct 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-Instruct-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

29 files · 84.7 GBWeights 84.7 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 29 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md1.01 KBc0df2f45f64fb2c6795cd24bc5bf8ad6bb941fce1f65ed4604e4024a27117902
added_tokens.json707 Bc0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680
chat_template.jinja4.04 KB40c21f34cf67d8c760ef72f8ad3ae5afad514299d4b06e91dd9a8d705af7b541
config.json22.1 KBfbad6dba0a785292119b904e03b52a0968929de51d115a27e99c8722f0ca279d
generation_config.json221 Bd7115cb81df546589f9937943302901a1b75b08909293d1fc96782750b1c3217
merges.txt1.67 MB8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
model-00001-of-00017.safetensors5.01 GB69212b74e2df87b9833ad87e760e57eb7f08696f4a6b02403e9d8156990c12c3
model-00002-of-00017.safetensors5.25 GB1717986a067e311f673c31f7edfd9e9d538e9cc52d5da6c8e94c66eeffc4c75c
model-00003-of-00017.safetensors5.25 GB6d5f6864f2d71b7e3f1d398265cb52579fa145e69fb736dd49f7cfb6961195d1
model-00004-of-00017.safetensors5.25 GBc874edba149fc9fe996437c55aac0ae94c42a1a550f07380dc9ac035d0cfe3ea
model-00005-of-00017.safetensors5.25 GB17d4424fe93f4cffdce96363e88432fd6573d7fce7f983886676b65d57cebeb1
model-00006-of-00017.safetensors5.25 GB81277b1f4d652804a99d3c1e542f86d7af151a4a0333dfac45b6f39a893e5d86
model-00007-of-00017.safetensors5.25 GBa25c35603b1ac2e24807add882aafc4efc78359eab6165bd6dd0aa5fe26e273d
model-00008-of-00017.safetensors5.25 GB9fa640351fb7a50a2cdac92dffeb858bfa446fa0431da90c653984a6e43cf220
model-00009-of-00017.safetensors5.25 GB35d892b1ca72046bbbb2064d63d8f51512f44e35613822bdb22e75ade690b819
model-00010-of-00017.safetensors5.25 GB91de6a56183175387f74e6675357e8dc868476b7636155779a2e189f0d17d8c9
model-00011-of-00017.safetensors5.25 GB9b68135ce368214020623416d0f9dcb5151cb2cba279d4fafeb478d766667bcd
model-00012-of-00017.safetensors5.25 GB59e54744d407a5c3ea8acae4447de9754ff3253c36a8fda605ce15068fe531d3
model-00013-of-00017.safetensors5.25 GB50ae8b749303aee4fd6630de42ef3ee846b71ace885f89cb3ba4187fe3943fe8
model-00014-of-00017.safetensors5.25 GB018353e90b869469cdf9b623ea6009312fca9966e406b07095ef163df1ed529c
model-00015-of-00017.safetensors5.25 GBf97a992d4bf82eebc42ab742992d68b7552fda5bc50b7d0e20ff0c18d37aea68
model-00016-of-00017.safetensors5.25 GBbbcafdaa049cd446a35579b46ffaa0782a077ecf6912be17098d612600d30eb6
model-00017-of-00017.safetensors904 MB10a8f1634d022083e02866945c6f0b3db5b7f1e29c3cbeb4d38f45b3986d7682
model.safetensors.index.json173 KB06be09c9dcb2bc30524ebbf066f1ac2f97d73808a8eb9ada7d177f64ec94863d
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
fd52af0cc2 pinned now2026-11-15 05:12 UTC29 files · 84.7 GB

Use it

$ fw get mlx-community/Qwen3-Next-80B-A3B-Instruct-8bit
# manifest sha256 b1a0aac47458… · 84.7 GB · 29 files
$ fw verify ./Qwen3-Next-80B-A3B-Instruct-8bit mlx-community/Qwen3-Next-80B-A3B-Instruct-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-Next-80B-A3B-Instruct-8bit.json --dir ./Qwen3-Next-80B-A3B-Instruct-8bit $ python3 fw.py verify ./Qwen3-Next-80B-A3B-Instruct-8bit ./mlx-community__Qwen3-Next-80B-A3B-Instruct-8bit.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-Instruct-8bit --revision fd52af0cc2a4a37b60904c4b0251255aa7d3dda2 --local-dir ./Qwen3-Next-80B-A3B-Instruct-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-Next-80B-A3B-Instruct-8bit", revision="fd52af0cc2a4a37b60904c4b0251255aa7d3dda2") model = AutoModelForCausalLM.from_pretrained("mlx-community/Qwen3-Next-80B-A3B-Instruct-8bit", revision="fd52af0cc2a4a37b60904c4b0251255aa7d3dda2", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/Qwen3-Next-80B-A3B-Instruct-8bit --revision fd52af0cc2a4a37b60904c4b0251255aa7d3dda2

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
c0df2f45f64fb2c6795cd24bc5bf8ad6bb941fce1f65ed4604e4024a27117902
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-Instruct-8bitDate: 2026-11-15Commit: fd52af0Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/Qwen3-Next-80B-A3B-Instruct-8bit
Pinned commit
fd52af0cc2a4a37b60904c4b0251255aa7d3dda2
Manifest
Qwen3-Next-80B-A3B-Instruct-8bit.json · .minisig
Manifest sha256
b1a0aac47458fb924c251e84f1cb6d9ba2d8aed99196d6d3be25d179f00d319d
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-Instruct-8bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3-Next-80B-A3B-Instruct-8bit.json.minisig $ minisign -Vm Qwen3-Next-80B-A3B-Instruct-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-Next-80B-A3B-Instruct · 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-Instruct-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-Next-80B-A3B-Instruct-8bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/Qwen3-Next-80B-A3B-Instruct-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