CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.qwen / Qwen3.5-0.8B-decision
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.qwenSubject:

Qwen3.5-0.8B-decision

Date: 2026-11-15Commit: 6708695Signed: 2DC28CC7B26A283B ✓

Text classification model with 873M parameters. Safetensors weights, 1.87 GB in all. Published by mlx-community under Apache-2.0.

873M params1.87GBQwen3.5-0.8B-decisionsafetensorspermissive
FactsParams873MSize1.87 GBFormatssafetensorsTasktext classificationLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/Qwen3.5-0.8B-decision
# manifest sha256 6384b9ffb36a… · 1.87 GB · 19 files
$ fw verify ./Qwen3.5-0.8B-decision mlx-community/Qwen3.5-0.8B-decision
From sourceHosted (signed)mlx-community/Qwen3.5-0.8B-decisionLast check: 2026-11-15 03:36 UTC
Run at homeGet help

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

Fine-tune of Qwen3.5-0.8B.

Works with

Run8Fine-tune7Convert8Scan2

Runs with

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

TransformersLocalAItinygradTriton Inference ServerBentoMLCTranslate2ExLlamaV2LitServe
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
1.87 GB
Weights
1.84 GB (safetensors)
Parameters
873M
Formats
safetensors
Task
text classification
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/Qwen3.5-0.8B

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 03:36 UTCpassed

Model card

From the publisher at commit 6708695. Shown as plain text with links; images open at the publisher.

Qwen3.5-0.8B decision model#

Qwen3.5-0.8B turned into a decision model with optiq lora train --decision: a LoRA on the backbone and a new joint schema head that scores noul, choice and score questions in one pass. It runs on Apple Silicon through MLX and OptiQ (optiq serve exposes /v1/systemone).

Typed Decisions result#

Scored on the full 400-case test split (2,000 decisions) with the benchmark's own metrics.

ModelAccuracyKL from gold ↓Brier ↓ECE ↓p50 latency
This model0.7720.0970.0540.1770.34 s
gemma-4-e2b-it-OptiQ-4bit-decision0.8020.0720.0390.1810.99 s
clef-OptiQ-4bit (27B)0.7190.1890.1020.1189.7 s
Always answer the train-split average0.4890.3270.181––

Latency is one request per case with all five questions, on an Apple M3 Max.

This model was fitted on the benchmark's own train split and nothing else: 1,080 records. The test cases are disjoint from it, but they come from the same four workflows, so expect less on decisions of a different kind. The Clef models were trained on other data. Top-label calibration (ECE) is no better than Clef's.

Correction, 2026-10-11. This card first reported 0.512 accuracy. That was a bug: the adapter was saved with tensor names that mlx-lm could not place, so it loaded without its LoRA weights. The adapter file is fixed and the numbers above are from the fixed file.

Use#

pip install -U mlx-optiq
optiq serve --model mlx-community/Qwen3.5-0.8B-decision

Size on disk is 1.9 GB (bf16 backbone, LoRA adapter and head).

Trained and scored with OptiQ.

Files

19 files · 1.87 GBWeights 1.84 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 19 files with their sha256
FileSizesha256
.eval_results/typed-decisions.yaml2.11 KBffd9e1b3acc0d2edc1eab4c2a8991801333fd900ffba412e389c31108b1ac3da
.gitattributes1.57 KB34448b82c17d60fec9b65b1f093c115ddbaadc04beb1b0140b6bfed2e012a930
LICENSE11.5 KBbbedc3fda3305820b977265f01b8619d87570a6739de3a5582c3464840f1e57a
README.md2.01 KBc0fb287e9c00bc740496e3da0a8be5a703adc1604187224a3cd5767cfe89cb9d
adapter_config.json479 B2dd00f948e4bb6105456c74355e531384ee121fa3b7f156e1a3b9a2b3ed7b36f
adapters.safetensors40.9 MB7ad3e00365ba2ecf6ebf560f2addd040c7c266c5a80224680dad186a9a3df0a0
chat_template.jinja7.75 KB273d8e0e683b885071fb17e08d71e5f2a5ddfb5309756181681de4f5a1822d80
config.json2.91 KBb90b86f35c8e6925ef74ee04d0e758f0a845c83a42089ad82bbaa948de9b4204
decision_config.json97 B1e231096b3befa254d7e0b37637be2d91f764034353909df1275f0f9fa6a90d8
joint_head.safetensors54.7 MB2ab2666452878491c63daedef5eb5e11f098954099a80cf71e7ac0257e5fc08e
joint_head_config.json116 B99f65ef462b1c92d9304ad1acecbbab93506efc0ba8227c46582b4264d27aa30
merges.txt3.35 MBa9d356d7bdf1ef4949e3e748e95b8e10ad9d4e2e838eddc38a0a7b6b94d1db8d
model.safetensors-00001-of-00001.safetensors1.75 GB04b1c301231dd422b8860db31311ab2721511346a32cb1e079c4c4e5f1fe4696
model.safetensors.index.json50.9 KBd8a08838a613b025eb7952ed9db11696213e57e76a375661ef5c12f9dd5dcf4e
preprocessor_config.json390 B27225450ac9c6529872ee1924fcb0962ff5634834f817040f444118116f4e516
tokenizer.json12.8 MB5f9e4d4901a92b997e463c1f46055088b6cca5ca61a6522d1b9f64c4bb81cb42
tokenizer_config.json16.7 KB49e2b6e395f959f077f1e992b338919c0d4a9732fc6e613995e06557f843500c
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
67086958f4 pinned now2026-11-15 03:36 UTC19 files · 1.87 GB

Use it

$ fw get mlx-community/Qwen3.5-0.8B-decision
# manifest sha256 6384b9ffb36a… · 1.87 GB · 19 files
$ fw verify ./Qwen3.5-0.8B-decision mlx-community/Qwen3.5-0.8B-decision
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/mlx-community/Qwen3.5-0.8B-decision.json --dir ./Qwen3.5-0.8B-decision $ python3 fw.py verify ./Qwen3.5-0.8B-decision ./mlx-community__Qwen3.5-0.8B-decision.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Qwen3.5-0.8B-decision --revision 67086958f49ccc3385404ba835924e897ee57c8a --local-dir ./Qwen3.5-0.8B-decision
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
LICENSE
Text sha256
bbedc3fda3305820b977265f01b8619d87570a6739de3a5582c3464840f1e57a
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: Qwen3.5-0.8B-decisionDate: 2026-11-15Commit: 6708695Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/Qwen3.5-0.8B-decision
Pinned commit
67086958f49ccc3385404ba835924e897ee57c8a
Manifest
Qwen3.5-0.8B-decision.json · .minisig
Manifest sha256
6384b9ffb36a05725f0632edbeb78cea2d46bc9bc6a7dd9ce0ddad2367b31067
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 03:36 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3.5-0.8B-decision.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen3.5-0.8B-decision.json.minisig $ minisign -Vm Qwen3.5-0.8B-decision.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/Qwen3.5-0.8B · this model is a finetune 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/Qwen3.5-0.8B-decision
Open in Freeweights Studio

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

Signed manifest
minisign, key 2DC28CC7B26A283B. Qwen3.5-0.8B-decision.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/Qwen3.5-0.8B-decision

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