CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.qwen / Qwen3.8-27B-nvfp4
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.qwenSubject:

Qwen3.8-27B-nvfp4

Date: 2026-11-15Commit: f9cb649Signed: 2DC28CC7B26A283B ✓

Image text to text model with 27.4B parameters. Safetensors weights, 16.1 GB in all. Published by mlx-community under Apache-2.0.

27.4B params16.1GBQwen3.8-27B-nvfp4safetensorspermissive
FactsParams27.4BSize16.1 GBFormatssafetensorsTaskimage text to textLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/Qwen3.8-27B-nvfp4
# manifest sha256 de3d64f8c057… · 16.1 GB · 15 files
$ fw verify ./Qwen3.8-27B-nvfp4 mlx-community/Qwen3.8-27B-nvfp4
From sourceHosted (signed)mlx-community/Qwen3.8-27B-nvfp4Last check: 2026-11-15 05:07 UTC
Run at homeGet help

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

Quantized of Qwen3.8-27B.

Works with

Run23Fine-tune29Convert15Evaluate13Scan13Apps62
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
16.1 GB
Weights
16.1 GB (safetensors)
Parameters
27.4B
Formats
safetensors
Task
image text to text
License
Apache-2.0 (permissive)
Files
15, each with a sha256
Publisher
mlx-community
Added
2026-11-15
Section
alt.freeweights.qwen
Lineage

Original release from the publisher.

Base model: Qwen/Qwen3.8-27B

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 05:07 UTCpassed

Model card

From the publisher at commit f9cb649. Shown as plain text with links; images open at the publisher.

mlx-community/Qwen3.8-27B-nvfp4#

This model was converted to MLX format from Qwen/Qwen3.8-27B using mlx-vlm version 0.6.8. Refer to the original model card for more details on the model.

Use with mlx#

pip install -U mlx-vlm
python -m mlx_vlm.generate --model mlx-community/Qwen3.8-27B-nvfp4 --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>

Files

15 files · 16.1 GBWeights 16.1 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 15 files with their sha256
FileSizesha256
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
README.md634 Bcdf0553c099811d6f43f4b4cacce6d770ff65d6b669a169dea5901b9443ac410
chat_template.jinja8.95 KBc3cf9e34abf4f9e36c2d72165aa9c132d3e2a725b6c2586aaa3a8af9d7a81041
config.json4.93 KB7380cfc6eb77891381ee24e944e6bd0caed7a957707f2512ddd6effc82c7e706
generation_config.json202 Be70c136c1b78ddc1fb0905bac8e733a4dc448d4f852a5dd75143fffc70be550e
model-00001-of-00003.safetensors5.34 GBa9de796bfb40fbe757ff3e567d83d5d100906d6dd231c8b11c431cd97d3dc288
model-00002-of-00003.safetensors5.35 GB6020f10999fe3a1b052f80f1e838a4491ea35d40a3bb36897981c6ade1cb7a19
model-00003-of-00003.safetensors5.36 GB654cd2782dd2736c76d0bd6a139203bd944fd8de3ba84f4b38fbdcc49a8a41e5
model.safetensors.index.json167 KB8a3f70b51e57843efcb417829dc8be081e414517995234e71fc7cf508ae01f90
preprocessor_config.json390 B27225450ac9c6529872ee1924fcb0962ff5634834f817040f444118116f4e516
processor_config.json991 B45fc17c8dd2474af6b493b52483c26c0584b0082d368c480f9fa611e73070040
tokenizer.json12.8 MB0997f410c57a1f4e53b09e4be8f4a172d90edd9564368fb0847030937229b9f3
tokenizer_config.json1.17 KB792fa3f0cb88b111e54ef3134c873531008c4df471d108da17903426e308aa7b
video_preprocessor_config.json385 B7768af27c1fafa9cc9011c1dc20067e03f8915e03b63504550e11d5066986d13
vocab.json6.72 MBce99b4cb2983d118806ce0a8b777a35b093e2000a503ebde25853284c9dfa003
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
f9cb649505 pinned now2026-11-15 05:07 UTC15 files · 16.1 GB

Use it

$ fw get mlx-community/Qwen3.8-27B-nvfp4
# manifest sha256 de3d64f8c057… · 16.1 GB · 15 files
$ fw verify ./Qwen3.8-27B-nvfp4 mlx-community/Qwen3.8-27B-nvfp4
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/Qwen3.8-27B-nvfp4.json --dir ./Qwen3.8-27B-nvfp4 $ python3 fw.py verify ./Qwen3.8-27B-nvfp4 ./mlx-community__Qwen3.8-27B-nvfp4.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Qwen3.8-27B-nvfp4 --revision f9cb6495054684578f19bf751882716f87542a96 --local-dir ./Qwen3.8-27B-nvfp4
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForImageTextToText, AutoProcessor processor = AutoProcessor.from_pretrained("mlx-community/Qwen3.8-27B-nvfp4", revision="f9cb6495054684578f19bf751882716f87542a96") model = AutoModelForImageTextToText.from_pretrained("mlx-community/Qwen3.8-27B-nvfp4", revision="f9cb6495054684578f19bf751882716f87542a96", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve mlx-community/Qwen3.8-27B-nvfp4 --revision f9cb6495054684578f19bf751882716f87542a96
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
cdf0553c099811d6f43f4b4cacce6d770ff65d6b669a169dea5901b9443ac410
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: Qwen3.8-27B-nvfp4Date: 2026-11-15Commit: f9cb649Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/Qwen3.8-27B-nvfp4
Pinned commit
f9cb6495054684578f19bf751882716f87542a96
Manifest
Qwen3.8-27B-nvfp4.json · .minisig
Manifest sha256
de3d64f8c05782cd4914b30ac21b73d37d15834f2ecb07081babf8940aad48ab
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:07 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3.8-27B-nvfp4.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3.8-27B-nvfp4.json.minisig $ minisign -Vm Qwen3.8-27B-nvfp4.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/Qwen3.8-27B · 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/Qwen3.8-27B-nvfp4
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. Qwen3.8-27B-nvfp4.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/Qwen3.8-27B-nvfp4

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