Downloads · 30 days
256
7% of all-time downloads
PersonaPlex-7B-MLX-8bit
aufklarer/PersonaPlex-7B-MLX-8bit
PersonaPlex-7B-MLX-8bit is a audio-to-audio model from aufklarer. Use it for the audio-to-audio task on the model card, and read the license before you ship it in a product. It is set up for mlx. The card lists the license as cc-by-nc-4.0.
PersonaPlex 7B full-duplex speech-to-speech model converted to MLX safetensors with 8-bit quantization for Apple Silicon.
All-time downloads
3.5K
Public
Repo size
9.8 GB
Likes
15
Trending 1
Repo makeup
Click a slice to open those files.
.safetensors9.8 GB · 100%
At a glance
- Task
- Audio-to-Audio
- Library
- mlx
- License
- cc-by-nc-4.0
- Model type
- personaplex
- Access
- Public
- Created
- Mar 2, 2026
- Updated
- Apr 12, 2026
- SHA
- 170375cc
Base models
Model card
From the Hugging Face model README
PersonaPlex-7B MLX 8-bit
PersonaPlex 7B full-duplex speech-to-speech model converted to MLX safetensors with 8-bit quantization for Apple Silicon.
Converted from nvidia/personaplex-7b-v1 (based on Kyutai Moshi architecture).
Swift inference: soniqo/speech-swift
Model Details
| Component | Architecture | Size |
|---|---|---|
| Temporal Transformer | 32-layer, 4096d, 32 heads (7B params) | ~6.5 GB (8-bit) |
| Depformer | 6-layer, 1024d, 16 heads, per-codebook weights | ~1.3 GB (8-bit) |
| Mimi Codec | SEANet encoder/decoder + 8L transformer + 16 RVQ codebooks | ~370 MB (fp16) |
| Embeddings | Text + 16 audio embeddings + output heads | ~940 MB (fp16) |
| Total | ~9.1 GB |
Usage
let model = try await PersonaPlexModel.fromPretrained(
modelId: "aufklarer/PersonaPlex-7B-MLX-8bit"
)
let response = model.respond(audio: samples, voice: .NATF0, steps: 100)
audio personaplex input.wav --model aufklarer/PersonaPlex-7B-MLX-8bit -o output.wav
Variants
| Variant | Quantization | Size | Model ID |
|---|---|---|---|
| 4-bit | 4-bit | ~4.9 GB | aufklarer/PersonaPlex-7B-MLX-4bit |
| 8-bit | 8-bit | ~9.1 GB | aufklarer/PersonaPlex-7B-MLX-8bit |
Voices
18 voice presets available: NATF0-3, NATM0-3, VARF0-4, VARM0-4
- Guide: soniqo.audio/guides/respond
- Docs: soniqo.audio
- GitHub: soniqo/speech-swift
- Task
- Audio-to-Audio
- Library
- mlx
- Type
- personaplex
- License
- cc-by-nc-4.0
- Languages
- en
- Created
- Mar 2, 2026
- Updated
- Apr 12, 2026