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

Qwen3-Coder-Next-4bit

Date: 2026-11-15Commit: 7b9321eSigned: 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-Coder-Next-4bitsafetensorspermissive
FactsParams79.7BSize44.9 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/Qwen3-Coder-Next-4bit
# manifest sha256 0abd2a12ae7c… · 44.9 GB · 19 files
$ fw verify ./Qwen3-Coder-Next-4bit mlx-community/Qwen3-Coder-Next-4bit
From sourceHosted (signed)mlx-community/Qwen3-Coder-Next-4bitLast check: 2026-11-15 04:52 UTC
Run at homeGet 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
44.9 GB
Weights
44.8 GB (safetensors)
Parameters
79.7B
Formats
safetensors
Task
text generation
License
Apache-2.0 (permissive)
Files
19, 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 04:52 UTCpassed

Model card

From the publisher at commit 7b9321e. Shown as plain text with links; images open at the publisher.

mlx-community/Qwen3-Coder-Next-4bit#

This model mlx-community/Qwen3-Coder-Next-4bit 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-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, return_dict=False,
    )

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

Files

19 files · 44.9 GBWeights 44.8 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 19 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md941 B64cc07a369b3e8f45e2dbc170afd2ad8b6d1a564f4db4a9901e5c4ec69c9bf61
chat_template.jinja6.07 KBc79a833039a43602150cce0902403d6e376c50930c1b2a139b2964e1f0c322a0
config.json22.2 KBe8e2412abc210311363cad4396e12fc73e8142e81408ca241b2487cc80723a29
generation_config.json214 B37a3c1ef63516ca489c575f0db1c0405ddc0c3dbaca9ed987344c966c37aeef5
model-00001-of-00009.safetensors5.13 GBfb30a2722004cb427d9dc3b3583a9dc4f94badf68420393324e6ebee4432c96f
model-00002-of-00009.safetensors5.26 GBa6b2a95a4bb7463f74951a5565e2504e7f28fe78877bb966378003b0def69038
model-00003-of-00009.safetensors5.24 GB0b8e009bd09fb5994d4d188a61e28a90aead48a50d7e0983d3bd7fc3644553d3
model-00004-of-00009.safetensors5.26 GB6b34fd01a609db8bd4e445dcc0cc1ef5991550523b4df7e89f59c7d50343e321
model-00005-of-00009.safetensors5.26 GBf19b843ee11c5b4c8d56b2a5940033e81ec29013de75d944447754238344621b
model-00006-of-00009.safetensors5.24 GB37f9b2ff202e8d58239f1df6acc568cb08e10a324b57c19f21b38ce93608b8c0
model-00007-of-00009.safetensors5.26 GB78e4b432212f783db393bc643b9875918fc050c3d3c41a071bf9260449db356a
model-00008-of-00009.safetensors5.26 GB3841f088f9ceed8f4024e0c6496677af6b6a32047f762337b6d42232261cb3dc
model-00009-of-00009.safetensors2.93 GB933efe2e2f28f97b9b851839c43fca0d6742b26c9ff9df1fd0e427712246553c
model.safetensors.index.json173 KB4ab1fbfbc6e42a84c6b810745765db249350ab1df1d1cdb0c2841de89e8ca309
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
7b9321eabb pinned now2026-11-15 04:52 UTC19 files · 44.9 GB

Use it

$ fw get mlx-community/Qwen3-Coder-Next-4bit
# manifest sha256 0abd2a12ae7c… · 44.9 GB · 19 files
$ fw verify ./Qwen3-Coder-Next-4bit mlx-community/Qwen3-Coder-Next-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-Coder-Next-4bit.json --dir ./Qwen3-Coder-Next-4bit $ python3 fw.py verify ./Qwen3-Coder-Next-4bit ./mlx-community__Qwen3-Coder-Next-4bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Qwen3-Coder-Next-4bit --revision 7b9321eabb85ce79625cac3f61ea691e4ea984b5 --local-dir ./Qwen3-Coder-Next-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-Coder-Next-4bit", revision="7b9321eabb85ce79625cac3f61ea691e4ea984b5") model = AutoModelForCausalLM.from_pretrained("mlx-community/Qwen3-Coder-Next-4bit", revision="7b9321eabb85ce79625cac3f61ea691e4ea984b5", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/Qwen3-Coder-Next-4bit --revision 7b9321eabb85ce79625cac3f61ea691e4ea984b5
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
64cc07a369b3e8f45e2dbc170afd2ad8b6d1a564f4db4a9901e5c4ec69c9bf61
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-4bitDate: 2026-11-15Commit: 7b9321eSigned: 2DC28CC7B26A283B ✓
Upstream
mlx-community/Qwen3-Coder-Next-4bit
Pinned commit
7b9321eabb85ce79625cac3f61ea691e4ea984b5
Manifest
Qwen3-Coder-Next-4bit.json · .minisig
Manifest sha256
0abd2a12ae7ca08353fc1478e175842134bd0c7e240f85b97f90b20f629e811e
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 04:52 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

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