CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.qwen / Qwen2-Audio-7B-Instruct-4bit
From: mlx-community <huggingface.co/mlx-community>Newsgroups: alt.freeweights.qwenSubject:

Qwen2-Audio-7B-Instruct-4bit

Date: 2026-11-15Commit: c655700Signed: 2DC28CC7B26A283B ✓

Audio text to text model. Safetensors weights, 6.57 GB in all. Published by mlx-community under Apache-2.0.

qwen6.57GBQwen2-Audio-7B-Instruct-4bitsafetensorspermissive
FactsParamsnot statedSize6.57 GBFormatssafetensorsTaskaudio text to textLicenseApache-2.0From sourcepermissive
$ fw get mlx-community/Qwen2-Audio-7B-Instruct-4bit
# manifest sha256 be77b51ee4b2… · 6.57 GB · 9 files
$ fw verify ./Qwen2-Audio-7B-Instruct-4bit mlx-community/Qwen2-Audio-7B-Instruct-4bit
From sourceHosted (signed)mlx-community/Qwen2-Audio-7B-Instruct-4bitLast check: 2026-11-15 02:51 UTC
Run at homeGet help

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

Fine-tune of Qwen2-Audio-7B-Instruct.

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
6.57 GB
Weights
6.56 GB (safetensors)
Parameters
not stated
Formats
safetensors
Task
audio text to text
License
Apache-2.0 (permissive)
Files
9, 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-Audio-7B-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 02:51 UTCpassed

Model card

From the publisher at commit c655700. Shown as plain text with links; images open at the publisher.

Qwen2-Audio-7B-Instruct (4-bit MLX)#

4-bit quantized version of Qwen/Qwen2-Audio-7B-Instruct for Apple Silicon via mlx-audio.

Usage#

from mlx_audio.stt.utils import load_model

model = load_model("mlx-community/Qwen2-Audio-7B-Instruct-4bit")

# Transcription
result = model.generate("audio.wav", prompt="Transcribe the audio.")
print(result.text)

# Audio understanding
result = model.generate("audio.wav", prompt="What emotion is the speaker expressing?")
print(result.text)

# Translation
result = model.generate("audio.wav", prompt="Translate the speech to French.")
print(result.text)

Model Details#

  • Base model: Qwen/Qwen2-Audio-7B-Instruct
  • Quantization: 4-bit (group_size=64), LLM only (encoder and projector kept in bf16)
  • Size: ~4.2GB (vs ~15GB bf16)
  • Architecture: Whisper-style encoder (32 layers) + Linear projector + Qwen2-7B LLM

Capabilities#

  • Speech transcription (ASR)
  • Speech translation
  • Audio captioning
  • Emotion / sentiment detection
  • Environmental sound classification
  • Music understanding
  • Voice chat (audio-only input)

Performance#

Tested on Apple Silicon (M-series):

  • ~4.7 tokens/sec generation (4-bit)
  • Accurate transcription matching HuggingFace reference

Conversion#

Converted using mlx-audio with:

  • Audio encoder: bf16 (not quantized)
  • Multi-modal projector: bf16 (not quantized)
  • Language model: 4-bit quantized (group_size=64)

Files

9 files · 6.57 GBWeights 6.56 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 9 files with their sha256
FileSizesha256
.gitattributes1.52 KB11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361
README.md1.72 KB1cddc760431c9c2c043ed4d17d9c17716a1f81978e6093389420cd46e7f2ce6d
config.json913 B39493dad1678533cc2a7ba2de0a573cc926a78ef4c7abef72a6b660159de94b7
merges.txt1.67 MB599bab54075088774b1733fde865d5bd747cbcc7a547c5bc12610e874e26f5e3
preprocessor_config.json342 B4cd7c6c061fe79244c57b0c320b2873f3ee5acce2277f7cc3aced042725680f2
tokenizer.json7.03 MBf7c9b2dba4a296b1aa76c16a34b8225c0c118978400d4bb66bff0902d702f5b8
tokenizer_config.json638 KBc738158e70eeecf25736a6c4d8e5f34cfce683079980757edfb0665a7b2457ed
vocab.json2.78 MBca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
weights.safetensors6.56 GB0967cde270ad62aa4824f0bbce283d0a2a6da2825ccf587640753c527d4174da
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
c655700026 pinned now2026-11-15 02:51 UTC9 files · 6.57 GB

Use it

$ fw get mlx-community/Qwen2-Audio-7B-Instruct-4bit
# manifest sha256 be77b51ee4b2… · 6.57 GB · 9 files
$ fw verify ./Qwen2-Audio-7B-Instruct-4bit mlx-community/Qwen2-Audio-7B-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/Qwen2-Audio-7B-Instruct-4bit.json --dir ./Qwen2-Audio-7B-Instruct-4bit $ python3 fw.py verify ./Qwen2-Audio-7B-Instruct-4bit ./mlx-community__Qwen2-Audio-7B-Instruct-4bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download mlx-community/Qwen2-Audio-7B-Instruct-4bit --revision c65570002626f41b4dc08b7b54f42f99f3e82e7f --local-dir ./Qwen2-Audio-7B-Instruct-4bit
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
1cddc760431c9c2c043ed4d17d9c17716a1f81978e6093389420cd46e7f2ce6d
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-Audio-7B-Instruct-4bitDate: 2026-11-15Commit: c655700Signed: 2DC28CC7B26A283B ✓
Upstream
mlx-community/Qwen2-Audio-7B-Instruct-4bit
Pinned commit
c65570002626f41b4dc08b7b54f42f99f3e82e7f
Manifest
Qwen2-Audio-7B-Instruct-4bit.json · .minisig
Manifest sha256
be77b51ee4b2820752509b2e63914611f2d49dd6f9fd8f64511523747285852b
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 02:51 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen2-Audio-7B-Instruct-4bit.json $ curl -O https://freeweights.allternit.com/manifests/mlx-community/Qwen2-Audio-7B-Instruct-4bit.json.minisig $ minisign -Vm Qwen2-Audio-7B-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/Qwen2-Audio-7B-Instruct · 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/Qwen2-Audio-7B-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. Qwen2-Audio-7B-Instruct-4bit.json. Provenance. Takedown history: none.
Source
huggingface.co/mlx-community/Qwen2-Audio-7B-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