Downloads · 30 days
24
11% of all-time downloads
personaplex-7b-nf4
cudabenchmarktest/personaplex-7b-nf4
personaplex-7b-nf4 is a machine learning model from cudabenchmarktest. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as other.
Quantized version of nvidia/personaplex-7b-v1 for edge deployment on NVIDIA Jetson AGX Orin and other memory-constrained devices.
All-time downloads
221
Public
Repo size
7.1 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors7.1 GB · 100%
At a glance
- License
- other
- Model type
- personaplex
- Access
- Public
- Created
- Mar 28, 2026
- Updated
- Mar 29, 2026
- SHA
- 8246e98d
Base models
Model card
From the Hugging Face model README
PersonaPlex 7B — INT4 NF4 Quantized
Quantized version of nvidia/personaplex-7b-v1 for edge deployment on NVIDIA Jetson AGX Orin and other memory-constrained devices.
Specs
| Original | Quantized | |
|---|---|---|
| Size | 15.59 GB | 4.14 GB |
| Precision | bf16 | INT4 (NF4) |
| Compression | 1x | 3.8x |
| Tensors quantized | — | 398/475 |
| Tensors kept fp16 | — | 77 (norms, biases, embeddings) |
Quantization Method
Symmetric per-group INT4 quantization with group_size=64:
- Weight matrices ≥4096 elements quantized to 4-bit
- Norms, biases, and embeddings kept in fp16 for quality
- Packed as uint8 (two INT4 values per byte)
- Per-group scales stored as fp16
Target Hardware
- Jetson AGX Orin 64GB: 17ms weight loading per frame (vs 68ms at bf16) — real-time full-duplex at 12.5 fps
- Jetson AGX Orin 32GB: Fits comfortably (~6GB with runtime overhead)
- Any GPU with ≥8GB VRAM: Enables PersonaPlex on consumer GPUs
Included Files
- — Quantized model weights
- — High-fidelity voice cloning with preprocessing (denoise, normalize, multi-segment averaging)
- — Script to reproduce this quantization
- — Example cloned voice embedding
Quick Start
from huggingface_hub import hf_hub_download
# No HF token needed — this repo is public
weight_path = hf_hub_download("cudabenchmarktest/personaplex-7b-nf4", "model-nf4.safetensors", token=False)
# Dequantize to bf16 for standard loading
from dequant_loader import dequant_nf4
# Or use with personaplex-setup server:
# python -m moshi.server --moshi-weight model-nf4.safetensors --device cuda
Server Usage
# Load NF4 (auto-dequants to bf16 at startup, ~16GB VRAM)
python -m moshi.server --moshi-weight model-nf4.safetensors --device cuda
# With CPU Mimi (saves ~840MB)
python -m moshi.server --moshi-weight model-nf4.safetensors --cpu-mimi --device cuda
Voice Cloning
python clone-voice.py --input my_voice.wav --name MyVoice --device cuda
Included Files
| File | Description |
|---|---|
model-nf4.safetensors | INT4 NF4 quantized weights (4.14 GB) |
linear2bit.py | Native 2-bit module (for turbo2bit, included for reference) |
dequant-loader.py | Programmatic dequantizer |
clone-voice.py | Voice cloning with LuxTTS preprocessing |
quantize-weights.py | Reproduce this quantization |
tokenizer-*.safetensors | Mimi audio codec |
tokenizer_spm_32k_3.model | Text tokenizer |
License
Same as the base model: NVIDIA Open Model License
Credits
Quantized by open-agents-ai for edge deployment. Base model by NVIDIA Research (PersonaPlex paper).
- Type
- personaplex
- License
- other
- Created
- Mar 28, 2026
- Updated
- Mar 29, 2026