MMLForge Search models, datasets, tasks… Start free
Home › Models › Audio To Audio › aufklarer/PersonaPlex-7B-MLX-4bit
P

aufklarer/PersonaPlex-7B-MLX-4bit

Audio To Audio·aufklarer· 206.4K· 37
mlx cc-by-nc-4.0 Audio To Audio arxiv:2504.07966base_model:nvidia/personaplex-7b-v1base_model:finetune:nvidia/personaplex-7b-v1license:cc-by-nc-4.0

Note: For full-duplex (real-time) inference, use the 8-bit variant instead. 4-bit quantization degrades PersonaPlex response quality significantly — INT8 is both 30% faster (112ms vs 158ms/step) and produces coherent responses where INT4 generates garbled output.

Open in MLForge Sign up free Desktop app Source ↗
# pull & run locally
pip install mlforge-sdk && mlforge pull aufklarer/PersonaPlex-7B-MLX-4bit

Model details

Task
Audio To Audio
Provider
aufklarer
Framework
mlx
Size
19 GB
License
cc-by-nc-4.0
Downloads
206.4K
Likes
37
Paper
arXiv:2504.07966
Updated
2026-04-12

About aufklarer/PersonaPlex-7B-MLX-4bit

Note: For full-duplex (real-time) inference, use the 8-bit variant instead. 4-bit quantization degrades PersonaPlex response quality significantly — INT8 is both 30% faster (112ms vs 158ms/step) and produces coherent responses where INT4 generates garbled output.

Related Audio To Audio

B nvidia/bigvgan_v2_22khz_80band_256x Audio To Audio 1.6M 29 🤗 HF B nvidia/bigvgan_v2_44khz_128band_512x Audio To Audio 500.6K 75 🤗 HF D aufklarer/DeepFilterNet3-CoreML Audio To Audio 210.5K 2 🤗 HF N neuphonic/neucodec Audio To Audio 188.6K 108 🤗 HF T JusperLee/TIGER-DnR Audio To Audio ·4.2M params 145.4K 23 🤗 HF Q Qwen/Qwen3-TTS-Tokenizer-12Hz Audio To Audio ·170.6M params 92.9K 70 🤗 HF

Browse all Audio To Audio models →