CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.qwen / Qwen2.5-Coder-32B-Instruct-6bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.qwenSubject:

Qwen2.5-Coder-32B-Instruct-6bit

Date: 2026-11-15Commit: 2538d7dSigned: 2DC28CC7B26A283B ✓

Text generation model with 32.8B parameters. Safetensors weights, 26.6 GB in all. Published by mlx-community under Apache-2.0.

32.8B params26.6GBQwen2.5-Coder-32B-Instruct-6bitsafetensorspermissive
FactsParams32.8BSize26.6 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/Qwen2.5-Coder-32B-Instruct-6bit
# manifest sha256 5f74a8fe093d… · 26.6 GB · 16 files
$ fw verify ./Qwen2.5-Coder-32B-Instruct-6bit mlx-community/Qwen2.5-Coder-32B-Instruct-6bit
From sourceHosted (signed)mlx-community/Qwen2.5-Coder-32B-Instruct-6bitLast check: 2026-11-15 05:08 UTC
Run at homeGet help

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

Quantized of Qwen2.5-Coder-32B-Instruct.

Works with

Run24Fine-tune29Convert15Evaluate13Scan13Apps58
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
26.6 GB
Weights
26.6 GB (safetensors)
Parameters
32.8B
Formats
safetensors
Task
text generation
License
Apache-2.0 (permissive)
Files
16, each with a sha256
Publisher
mlx-community
Added
2026-11-15
Section
alt.freeweights.qwen
Lineage

Original release from the publisher.

Base model: Qwen/Qwen2.5-Coder-32B-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 05:08 UTCpassed

Model card

From the publisher at commit 2538d7d. Shown as plain text with links; images open at the publisher.

mlx-community/Qwen2.5-Coder-32B-Instruct-6bit#

The Model mlx-community/Qwen2.5-Coder-32B-Instruct-6bit was converted to MLX format from Qwen/Qwen2.5-Coder-32B-Instruct using mlx-lm version 0.19.3.

Use with mlx#

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Qwen2.5-Coder-32B-Instruct-6bit")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

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

Files

16 files · 26.6 GBWeights 26.6 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 16 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md1.13 KB1d20c0253f7e72640479737adb86e36d657317b22364299144dc763797fd112c
added_tokens.json605 B58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b
config.json867 Bcbabe761dc49f34765859c117c8831f924731d85b01f598af88eedd63dee7004
merges.txt1.67 MB8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
model-00001-of-00006.safetensors5.27 GB3b15ba0f044db718a14227c6fa572052bcc557da2e8e692e04d0cbbdcffae601
model-00002-of-00006.safetensors5.32 GB2569d9218ec4f00f5e20afd5bd9a0f9b87548afb33db27ae24e9ab4c640e2142
model-00003-of-00006.safetensors5.27 GBce152de16bd30fc90f44ec6d060c38991f65facc4c1943f0604f5c48ea7608f4
model-00004-of-00006.safetensors5.27 GB85a026334d39a4963d2bf69ca394ff2c1a3b4623c6f0462061769863270b630f
model-00005-of-00006.safetensors4.87 GB64f0c5331133f9a71facc8c8a80ef933778e20a9e5484ae7df8ee978736fcd66
model-00006-of-00006.safetensors633 MB2290e0fe506787e239b9feaf3bf6c2922440a6e46b21eb962910712c0d950d8b
model.safetensors.index.json143 KB87801e4dac5b379689e5b2240fe6533037af8e28a4c839385a8907e0cacae868
special_tokens_map.json613 B76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
tokenizer.json11.4 MB9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
tokenizer_config.json7.30 KB959e7f1d9a1b7641a6d6ce05ca97b75c7894fcb66cbe5a040406458fb1128ee4
vocab.json2.78 MBca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
2538d7dacc pinned now2026-11-15 05:08 UTC16 files · 26.6 GB

Use it

$ fw get mlx-community/Qwen2.5-Coder-32B-Instruct-6bit
# manifest sha256 5f74a8fe093d… · 26.6 GB · 16 files
$ fw verify ./Qwen2.5-Coder-32B-Instruct-6bit mlx-community/Qwen2.5-Coder-32B-Instruct-6bit
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/Qwen2.5-Coder-32B-Instruct-6bit.json --dir ./Qwen2.5-Coder-32B-Instruct-6bit $ python3 fw.py verify ./Qwen2.5-Coder-32B-Instruct-6bit ./mlx-community__Qwen2.5-Coder-32B-Instruct-6bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Qwen2.5-Coder-32B-Instruct-6bit --revision 2538d7dacc2cd8089e76f5c346c189e150aa0fdd --local-dir ./Qwen2.5-Coder-32B-Instruct-6bit
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/Qwen2.5-Coder-32B-Instruct-6bit", revision="2538d7dacc2cd8089e76f5c346c189e150aa0fdd") model = AutoModelForCausalLM.from_pretrained("mlx-community/Qwen2.5-Coder-32B-Instruct-6bit", revision="2538d7dacc2cd8089e76f5c346c189e150aa0fdd", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/Qwen2.5-Coder-32B-Instruct-6bit --revision 2538d7dacc2cd8089e76f5c346c189e150aa0fdd
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
1d20c0253f7e72640479737adb86e36d657317b22364299144dc763797fd112c
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: Qwen2.5-Coder-32B-Instruct-6bitDate: 2026-11-15Commit: 2538d7dSigned: 2DC28CC7B26A283B ✓
Upstream
mlx-community/Qwen2.5-Coder-32B-Instruct-6bit
Pinned commit
2538d7dacc2cd8089e76f5c346c189e150aa0fdd
Manifest
Qwen2.5-Coder-32B-Instruct-6bit.json · .minisig
Manifest sha256
5f74a8fe093dabb3b33154e44192d214e7aced637b2060f9ae1a02dffb8c1d87
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:08 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen2.5-Coder-32B-Instruct-6bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen2.5-Coder-32B-Instruct-6bit.json.minisig $ minisign -Vm Qwen2.5-Coder-32B-Instruct-6bit.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/Qwen2.5-Coder-32B-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/Qwen2.5-Coder-32B-Instruct-6bit
Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest
minisign, key 2DC28CC7B26A283B. Qwen2.5-Coder-32B-Instruct-6bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/Qwen2.5-Coder-32B-Instruct-6bit

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