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

Qwen3-Coder-Next-8bit

Date: 2026-11-15Commit: 6d3c664Signed: 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-Coder-Next-8bitsafetensorspermissive
FactsParams79.7BSize84.7 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/Qwen3-Coder-Next-8bit
# manifest sha256 6bff9485c0b0… · 84.7 GB · 27 files
$ fw verify ./Qwen3-Coder-Next-8bit mlx-community/Qwen3-Coder-Next-8bit
From sourceHosted (signed)mlx-community/Qwen3-Coder-Next-8bitLast check: 2026-11-15 04:57 UTC
Get help

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

Quantized of Qwen3-Coder-Next.

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
27, 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-Coder-Next

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 04:57 UTCpassed

Model card

From the publisher at commit 6d3c664. Shown as plain text with links; images open at the publisher.

mlx-community/Qwen3-Coder-Next-8bit#

This model mlx-community/Qwen3-Coder-Next-8bit was converted to MLX format from Qwen/Qwen3-Coder-Next using mlx-lm version 0.30.5.

Use with mlx#

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Qwen3-Coder-Next-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, return_dict=False,
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)

Files

27 files · 84.7 GBWeights 84.7 GB (safetensors). Sizes and sha256 from the signed manifest.
Show all 27 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md941 B303f8c6597f92516274c70bb0f17853fe9ac359cf975cec871e1860ad898482e
chat_template.jinja6.07 KBc79a833039a43602150cce0902403d6e376c50930c1b2a139b2964e1f0c322a0
config.json22.2 KB5147979efd0d14009df38a7c81f1d8cc29728395f382da406c674cee6a06644b
generation_config.json214 B37a3c1ef63516ca489c575f0db1c0405ddc0c3dbaca9ed987344c966c37aeef5
model-00001-of-00017.safetensors5.01 GB5f9ab10da8272e7d6d4c53d916f81706b6c4b6d36dbaa3cb603030dbedb622fa
model-00002-of-00017.safetensors5.25 GB4418df9563555bcf5413e2e38ad235207cc98735143d02c3e6bd7e9a2f04cc06
model-00003-of-00017.safetensors5.25 GB433402b7ea8090a381c383d5e8bf52764642decbdaeff24ac68bd02a2e1c7eba
model-00004-of-00017.safetensors5.25 GB6fbc043e27f738ad0ea3d658777c5bf1db4a5e77c557f14492aeb934cabca953
model-00005-of-00017.safetensors5.25 GB894b5d4a524aaa46712fa643f1eb9d239e66746b97594adbf14c3f86124e9fc3
model-00006-of-00017.safetensors5.25 GB6e43a2dda889ac414ca014d69f123f21c42296db99d7e1b5a565a893ded0fbd4
model-00007-of-00017.safetensors5.25 GB35e134e18585bd79f83896a7abe76ac0b648aaa162cd27abc9d9ca371cdf73f4
model-00008-of-00017.safetensors5.25 GB37dacd3dd070981c4f093b6cac7cd101bf262967eeab160c371c9c3779a101e2
model-00009-of-00017.safetensors5.25 GB7ab8b11bbb3c7ef28bf4d7cc8ccc764fb7ed09883bc70ec142ad37145c885b9c
model-00010-of-00017.safetensors5.25 GBddd529dba1335d18ae4f644badc95c1053e5f172628cb62ea688daa7b35bc7ae
model-00011-of-00017.safetensors5.25 GBeff97b420def52688f9c3691dff837d1f7964904bcb6042de8c9a2656849b5b8
model-00012-of-00017.safetensors5.25 GBa0765861dbd3d79b5066e571d671563bd3923374985dec157ccdd0959f3a4298
model-00013-of-00017.safetensors5.25 GB1d24f5ec419d52dfa876eba312678a4fc5facbda15eec4c97f2a4a5decfe7dc6
model-00014-of-00017.safetensors5.25 GB8dc787e5fd81ad417f5f3ec2ee20ef278df0d71e1e5b0e135ee89f41a51585bd
model-00015-of-00017.safetensors5.25 GB51fecbc28d25994e03eb56621ea68f1e6a7d47bb39c65c25c9b8d75122e5306b
model-00016-of-00017.safetensors5.25 GB731aab1bb4f29e0d857c5fa6fa35c2d933adf7d17df9f8e79199f4c8298adbad
model-00017-of-00017.safetensors904 MBe1045fc969ea62487e2f6169594c3ede78025e18d30bfe6cdadb28b096f73839
model.safetensors.index.json173 KB06be09c9dcb2bc30524ebbf066f1ac2f97d73808a8eb9ada7d177f64ec94863d
qwen3_coder_detector_sgl.py19.9 KBe5a6112dd41df1580ede5f52e928e58cb74985dfa5628fd94073fd6a0f20fb8d
qwen3coder_tool_parser_vllm.py31.7 KBe6ad932aaa29a4004d592ca655c3d1ad849525a498ba60a716909ec9c1fda297
tokenizer.json11.4 MBbe75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
tokenizer_config.json702 B02222317d2b3586fe0676aaf7455a90fbe4b1e4f256b9f41fba3374357303ae2
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
6d3c664dc8 pinned now2026-11-15 04:57 UTC27 files · 84.7 GB

Use it

$ fw get mlx-community/Qwen3-Coder-Next-8bit
# manifest sha256 6bff9485c0b0… · 84.7 GB · 27 files
$ fw verify ./Qwen3-Coder-Next-8bit mlx-community/Qwen3-Coder-Next-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-Coder-Next-8bit.json --dir ./Qwen3-Coder-Next-8bit $ python3 fw.py verify ./Qwen3-Coder-Next-8bit ./mlx-community__Qwen3-Coder-Next-8bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Qwen3-Coder-Next-8bit --revision 6d3c664dc8539a711783391484fd6784c51fd8fa --local-dir ./Qwen3-Coder-Next-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-Coder-Next-8bit", revision="6d3c664dc8539a711783391484fd6784c51fd8fa") model = AutoModelForCausalLM.from_pretrained("mlx-community/Qwen3-Coder-Next-8bit", revision="6d3c664dc8539a711783391484fd6784c51fd8fa", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/Qwen3-Coder-Next-8bit --revision 6d3c664dc8539a711783391484fd6784c51fd8fa

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
303f8c6597f92516274c70bb0f17853fe9ac359cf975cec871e1860ad898482e
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-Coder-Next-8bitDate: 2026-11-15Commit: 6d3c664Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/Qwen3-Coder-Next-8bit
Pinned commit
6d3c664dc8539a711783391484fd6784c51fd8fa
Manifest
Qwen3-Coder-Next-8bit.json · .minisig
Manifest sha256
6bff9485c0b07d3aae4c76879d483e4464350826cd92abf78eb0dff16354265e
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 04:57 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3-Coder-Next-8bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3-Coder-Next-8bit.json.minisig $ minisign -Vm Qwen3-Coder-Next-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-Coder-Next · 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-Coder-Next-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-Coder-Next-8bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/Qwen3-Coder-Next-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