alt.freeweights.qwen / Qwen3-Coder-480B-A35B-Instruct-4bit

From:

mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.qwenSubject:

Qwen3-Coder-480B-A35B-Instruct-4bit

Date: 2026-11-15Commit: ca8dbf4Signed: 2DC28CC7B26A283B ✓

Text generation model with 480.2B parameters. Safetensors weights, 270 GB in all. Published by mlx-community under Apache-2.0.

480.2B params

270GBQwen3-Coder-480B-A35B-Instruct-4bitsafetensorspermissive

FactsParams480.2BSize270 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive

$ fw get mlx-community/Qwen3-Coder-480B-A35B-Instruct-4bit
# manifest sha256 1986ea0c6fd5… · 270 GB · 75 files
$ fw verify ./Qwen3-Coder-480B-A35B-Instruct-4bit mlx-community/Qwen3-Coder-480B-A35B-Instruct-4bit

From sourceHosted (signed)mlx-community/Qwen3-Coder-480B-A35B-Instruct-4bitLast check: 2026-11-15 05:09 UTC

Get help

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

Quantized of Qwen3-Coder-480B-A35B-Instruct.

Works with

Run24 Fine-tune29 Convert15 Evaluate13 Scan13 Apps58

Runs with

Ranked by fit to this model (safetensors), then by GitHub stars.

vLLM exo Text Generation WebUI

SGLang MLC LLM KTransformers LMCache Xinference LMDeploy mistral.rs Mooncake FlashInfer

Show all 24

AIBrix fastllm ExLlamaV3

Transformers LocalAI tinygrad gpu-unlock Triton Inference Server BentoML CTranslate2 ExLlamaV2 LitServe

Convert with

mergekit TensorRT Model Optimizer

LLM Compressor Neural Compressor AutoRound AQLM GPTQModel ONNX Core ML Tools ExecuTorch

Show all 15

Evaluate with

Opik DeepEval Ragas lm-evaluation-harness OpenCompass SWE-bench

simple-evals TruLens HELM

LightEval

Evaluate Weave

Show all 13

Autoevals

Scan with

promptfoo garak Guardrails NeMo Guardrails Giskard DeepTeam AI Fairness 360 Fairlearn Detoxify MCP Scanner AgentDojo ModelScan

Show all 13

picklescan

Overview Model card Files Use it License Provenance Model tree

Overview

Size: 270 GB
Weights: 270 GB (safetensors)
Parameters: 480.2B
Formats: safetensors
Task: text generation
License: Apache-2.0 (permissive)
Files: 75, 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-480B-A35B-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

Badge	Host	Last check	Result
From source	huggingface.co	2026-11-15 05:09 UTC	passed

Model card

From the publisher at commit ca8dbf4. Shown as plain text with links; images open at the publisher.

mlx-community/Qwen3-Coder-480B-A35B-Instruct-4bit#

This model mlx-community/Qwen3-Coder-480B-A35B-Instruct-4bit was converted to MLX format from Qwen/Qwen3-Coder-480B-A35B-Instruct using mlx-lm version 0.26.0.

Use with mlx#

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Qwen3-Coder-480B-A35B-Instruct-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

75 files · 270 GBWeights 270 GB (safetensors). Sizes and sha256 from the signed manifest.

Show all 75 files with their sha256

File	Size	sha256
.gitattributes	1.57 KB	34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md	1.03 KB	66da2b6671e17fa463f9666a4fdf2c6349b3ce22f4b99861224395a97758c14c
added_tokens.json	707 B	c0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680
chat_template.jinja	6.72 KB	672e747c77e990320152343b0a4951222e40de5645297905d89afba05586d827
config.json	1.22 KB	5a1e9c698e43e49283a008d7ef89e61daafe080f7a920681d2af1deb4e9472a3
generation_config.json	180 B	c99723ab3ba28630d26ae23def77603b540a46924895af5cf234740d3b27b51d
merges.txt	1.67 MB	8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
model-00001-of-00062.safetensors	4.96 GB	73418c8a92e57e2454fded53a5f84037d00607223b6e5cf272b907c674b8bad6
model-00002-of-00062.safetensors	4.34 GB	493fb824b1fc4f11fb64474a19c91dd81b3c62fc4f9a15024868c6ef30345097
model-00003-of-00062.safetensors	4.34 GB	3c93ab40408906a825ae5a5a15a5b2779d023b86c099ed942b528f1eaa773af8
model-00004-of-00062.safetensors	4.34 GB	b8fd47b9f771e2e3989f2f93925c8c9df315e233eaa0b9e005e66fd6dcfc3aac
model-00005-of-00062.safetensors	4.34 GB	fa154624e4ee27101cc81052495156764a67a5c3250ca2922bd22671fea2871f
model-00006-of-00062.safetensors	4.34 GB	ca7abb28bcafeb280a49641caf836ede28d7ffeef2b6125a9483127e67fd82fb
model-00007-of-00062.safetensors	4.34 GB	51c1dd7a9309ac71b5825a89359d3cd805acc8155e2f45af32c25c34e52c5af1
model-00008-of-00062.safetensors	4.34 GB	efc4028546e21d1f7d6eff3140383a5e66b3e6329f0b0c6e1004d41d7c1f8a2e
model-00009-of-00062.safetensors	4.34 GB	317985c1411d5efa12e6c4f090d1f6b5624fac5fc0d5f5385e221655ca485f51
model-00010-of-00062.safetensors	4.34 GB	02a9f2b4880750c5208205b14ace01559e73f7ae092c48161eb75956da2f1704
model-00011-of-00062.safetensors	4.34 GB	89df3f49970c9c6a87b17fd27fc4f903099cd34dcfca9479770369f376248592
model-00012-of-00062.safetensors	4.34 GB	0f5b58e83653c307cbd0af0e438e3146862907c809e6549e20c2caa9c97a2d5f
model-00013-of-00062.safetensors	4.34 GB	dc068479f3aa3168ca67ec16875e8e269967431efbc90c7943eb041820c08170
model-00014-of-00062.safetensors	4.34 GB	baa4fa1ee99a5824f5ad2dd5f4b3a9d04654498c50c8a7a1aa19385d505ef181
model-00015-of-00062.safetensors	4.34 GB	54d0e21c2a1731b65d7491c467170b7e0c246027a8a760e05faa327f216fd97c
model-00016-of-00062.safetensors	4.34 GB	173d0f580eab97f99cca468d821b66b821a93ee5b0252f98e9bb29de4f0313b6
model-00017-of-00062.safetensors	4.34 GB	3384b27f32aa2b8cf41433ecb35229a66987febdd4d73ed4eb91496e9cd46698
model-00018-of-00062.safetensors	4.34 GB	596f05e78c71a38f87e8e6808a0d7f7714d046115adc4029bebc51abb21a8f12
model-00019-of-00062.safetensors	4.34 GB	a2c8d2d5b31cc646af9fa09a2ea99b3b6a71eef5670aa5e2027c1c289f23b559
model-00020-of-00062.safetensors	4.34 GB	db229e55336ed702d91832e681b46ba743f8082704e5e9631080f4153134656c
model-00021-of-00062.safetensors	4.34 GB	4c246bd920137d46311932cb861c52ae546856d2b200d5db70179f47bbd7d38f
model-00022-of-00062.safetensors	4.34 GB	1a10596c418943e67e539b69432465045dcc2490546ba57fe10a6bd54038faf9
model-00023-of-00062.safetensors	4.34 GB	97e8b6143a4f0c29bafea3ff4c1104190ed7942a818eae56406c87ee0ab03422
model-00024-of-00062.safetensors	4.34 GB	be2e91bebdd2a27c8aa10bdc3c349b7675d808cf4329909593232af1db9630cc
model-00025-of-00062.safetensors	4.34 GB	d2b7c00b90120185e4cb9f8245ecfbd41a7e4099f2626bceaf43f4f822e310bf
model-00026-of-00062.safetensors	4.34 GB	ef33e8b771cf41ddbd584a1407d3c8f334fa02fd1b8d8f9500395251c77e1f81
model-00027-of-00062.safetensors	4.34 GB	9026a1e9316c30c2580cb91186e1e83f8b01b021a546e2c13de85c43fe4e6afd
model-00028-of-00062.safetensors	4.34 GB	d3a40571249de5ac09d8e25e1238bada33630ba1afb639d9a47c756af78e86e3
model-00029-of-00062.safetensors	4.34 GB	bebb05172e4315664d5f40fc659c697b76910d622c3c8b14b27fc1775cfb066e
model-00030-of-00062.safetensors	4.34 GB	fed8a71e5c8ed94e21e25f672a1c8ad10b6ca765496a53db10db95dfbab3b92c
model-00031-of-00062.safetensors	4.34 GB	25aafcf94d4ac83166281764544305edf6e0fb21bde9b0592e626305d4593443
model-00032-of-00062.safetensors	4.34 GB	1bf869641104b53da6531a1b064fe04b10fcfa533e2703d5f495dea5c1f13d07
model-00033-of-00062.safetensors	4.34 GB	cde9dac00d5cf4665b24a8fc67e680319162845659a3eac5088df3a2116451c9
model-00034-of-00062.safetensors	4.34 GB	fd9afc2905193cb4856baa32e090542b5d3e0e129dbf38b86c1edffcb1f6fb23
model-00035-of-00062.safetensors	4.34 GB	da9c6b57cc5a01f9fca6f7f65f81a8964db0dcc14ed8f2d3232310f61118d0b1
model-00036-of-00062.safetensors	4.34 GB	ed86023078623b34c591c35e3081494e9870ddfc597a113b9ee0b3dcaed794b6
model-00037-of-00062.safetensors	4.34 GB	942f2fcae1407f77809da65616a588d03e50d966613066cacddf7f9af36de872
model-00038-of-00062.safetensors	4.34 GB	33cca2cbe0477187ccc0495fa4722e3d234683f30e439a0db93d74ecbcf97297
model-00039-of-00062.safetensors	4.34 GB	dabd68d073a04f2b9bacf9c1985091660c5f5544d650e4966ea15564e9cdc5da
model-00040-of-00062.safetensors	4.34 GB	7d89fb25f7b8d6a96b13a79dbe89e58050515943594c1fccc14aae811f34a985
model-00041-of-00062.safetensors	4.34 GB	0ac6c0d9c3d4627c1686e435d64c2fdcb94eef59014d472ffd068d257ecbf664
model-00042-of-00062.safetensors	4.34 GB	5790e11a48b354a8ef7da4fa00224a908accf11581c33a66dabb6a10cda394c2
model-00043-of-00062.safetensors	4.34 GB	03d1ca898a94bb955df4a52791bb9b95b374e58c326816a07eef5fdfccdcca23
model-00044-of-00062.safetensors	4.34 GB	b43802c9cca1a4df1dae3d1cba3c4e66278946941bb4ca0eb4def537c5d59536
model-00045-of-00062.safetensors	4.34 GB	b2568de1c7628852189be3603ebaf0259eae802960e3126e018f8d81ecb0df67
model-00046-of-00062.safetensors	4.34 GB	5039cb6bb94285381b3e64a994a8cdffd9f2a6ed9c7e9ed17a6672d80008f114
model-00047-of-00062.safetensors	4.34 GB	379d59094686b15987b56a4c2127762aacf4bde113d244b65f1053d0070db1b6
model-00048-of-00062.safetensors	4.34 GB	c54cc83dcdb1d9c09e9e2b361f12b19a3d7d99c5a32bee3700a212d4f9957882
model-00049-of-00062.safetensors	4.34 GB	3a7e536dffa51e929f5eecc0363a7502e5ce300645aa50325c295a55c9934033
model-00050-of-00062.safetensors	4.34 GB	d136dce2ada0c7b4f661f898b45b5251f0b930a7997df9f28ad34c804c3a28ef
model-00051-of-00062.safetensors	4.34 GB	37dd1d361d878113051e5c47a7956b59612a97069f4a8b82975899636225ec72
model-00052-of-00062.safetensors	4.34 GB	3770611c65cf5a989e5d08a085c00428e1448554d3d6304c018fdb87e1bf5aea
model-00053-of-00062.safetensors	4.34 GB	966cef73325efabca877ab1dc1a1363bd6084b64cf9efee90eb653034e9202a2
model-00054-of-00062.safetensors	4.34 GB	9fe443c75346ccb576bc45b74f7a4e1adf235b171c985203bbe9fadc914bbd9a
model-00055-of-00062.safetensors	4.34 GB	81acd78169a7da8646ae0e147d7fef6eaee51f09b587b71d17d51db2b4268ebd
model-00056-of-00062.safetensors	4.34 GB	4afe9abc3f085f9d0bb788acb6c1e6e7cf34ca3daa4c27079fcae62e55048bec
model-00057-of-00062.safetensors	4.34 GB	af6a55911a05bd2d91c9ef2961ea72624ff33839da14cb872e4fffda04cb0bc0
model-00058-of-00062.safetensors	4.34 GB	a04ca8ce7665957d6a6a98731db7613e8db7649ca8d8558780094824fc62452d
model-00059-of-00062.safetensors	4.34 GB	108b4d77aa2121cb9568d5c35918a8a443b80b3e8a322d9d0c2c3a77ddcc4ca6
model-00060-of-00062.safetensors	4.34 GB	427f6b119c8a9bd43e0e21aa85635619312c552f53676416d99960379be4f94b
model-00061-of-00062.safetensors	4.34 GB	502cee02287bb143ee2b3d07a4df34dbbb533e73c83dff0aa44494572d62f805
model-00062-of-00062.safetensors	4.77 GB	95a67eca9f824989fac1a6b091b97a92141aa050da823c167a49b2f92dd092ad
model.safetensors.index.json	154 KB	1f8e584cecd5a6ac5ef230365f0c2c839e0d9e74dca75dad9f1f37d9a5e87458
qwen3_xml_tool_parser.py	28.9 KB	8265749a8e247732a9a0879278fe52efda2d1daa461ec8e3fb84d1e58b39531e
special_tokens_map.json	613 B	76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
tokenizer.json	11.4 MB	aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
tokenizer_config.json	5.41 KB	05a2d456eb807c8368fe6b60101b1d1160d6889071a751ed08576b96e77e01cd
vocab.json	2.78 MB	ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910

VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.

Upstream commit	Date	Contents
ca8dbf4107 pinned now	2026-11-15 05:09 UTC	75 files · 270 GB

Use it

$ fw get mlx-community/Qwen3-Coder-480B-A35B-Instruct-4bit
# manifest sha256 1986ea0c6fd5… · 270 GB · 75 files
$ fw verify ./Qwen3-Coder-480B-A35B-Instruct-4bit mlx-community/Qwen3-Coder-480B-A35B-Instruct-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-480B-A35B-Instruct-4bit.json --dir ./Qwen3-Coder-480B-A35B-Instruct-4bit
$ python3 fw.py verify ./Qwen3-Coder-480B-A35B-Instruct-4bit ./mlx-community__Qwen3-Coder-480B-A35B-Instruct-4bit.json

hfThe Hugging Face CLI with one setting. Same repo id.

$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Qwen3-Coder-480B-A35B-Instruct-4bit --revision ca8dbf41071f579fbe3260f20bbe1ab896f79031 --local-dir ./Qwen3-Coder-480B-A35B-Instruct-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-480B-A35B-Instruct-4bit", revision="ca8dbf41071f579fbe3260f20bbe1ab896f79031")
model = AutoModelForCausalLM.from_pretrained("mlx-community/Qwen3-Coder-480B-A35B-Instruct-4bit", revision="ca8dbf41071f579fbe3260f20bbe1ab896f79031", device_map="auto")

vLLMServe an OpenAI-compatible API.

$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/Qwen3-Coder-480B-A35B-Instruct-4bit --revision ca8dbf41071f579fbe3260f20bbe1ab896f79031

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: 66da2b6671e17fa463f9666a4fdf2c6349b3ce22f4b99861224395a97758c14c
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-480B-A35B-Instruct-4bitDate: 2026-11-15Commit: ca8dbf4Signed: 2DC28CC7B26A283B ✓

Upstream: mlx-community/Qwen3-Coder-480B-A35B-Instruct-4bit
Pinned commit: ca8dbf41071f579fbe3260f20bbe1ab896f79031
Manifest: Qwen3-Coder-480B-A35B-Instruct-4bit.json · .minisig
Manifest sha256: 1986ea0c6fd5f7167954a45d9f5c922f15eaae2ea70828a3a705fbe32da878cb
Signature: minisign, Ed25519, key 2DC28CC7B26A283B
Created: 2026-11-15 05:09 UTC
Generator: freeweights-manifest/0.1.0
Takedowns: None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3-Coder-480B-A35B-Instruct-4bit.json
$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3-Coder-480B-A35B-Instruct-4bit.json.minisig
$ minisign -Vm Qwen3-Coder-480B-A35B-Instruct-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-480B-A35B-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-Coder-480B-A35B-Instruct-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-480B-A35B-Instruct-4bit.json. Provenance. Takedown history: none.

Source

huggingface.co/mlx-community/Qwen3-Coder-480B-A35B-Instruct-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

Qwen3-Coder-480B-A35B-Instruct-4bit

Works with

Runs with

Fine-tune with

Convert with

Evaluate with

Scan with

Works with

Overview

Model card

mlx-community/Qwen3-Coder-480B-A35B-Instruct-4bit#

Use with mlx#

Files

Use it

License

Provenance

How to verify

Model tree

Related models