aufklarer / FlashSR-MLX-8bit

huggingface.co
Total runs: 39
24-hour runs: -2
7-day runs: 3
30-day runs: 0
Model's Last Updated: May 21 2026
audio-to-audio

Introduction of FlashSR-MLX-8bit

Model Details of FlashSR-MLX-8bit

FlashSR-MLX-8bit

MLX port of FlashSR — a single-step distilled latent-diffusion audio super-resolution model — quantized to INT8 weight-only for on-device inference on Apple Silicon. Upsamples any-rate input (mono) to 48 kHz in one diffusion pass with a specialised BigVGAN-flavour SR vocoder. FlashSR is the distilled student of AudioSR .

Model
Total parameters 638 M (VAE 223 M + UNet 258 M + Vocoder 157 M)
Diffusion steps 1 (distilled v-prediction student, cosine schedule, t=999)
Quantization INT8 weight-only, group size 64, mode mlx_affine_flat
Format MLX safetensors (single combined bundle)
Sample rate 48 kHz mono out (any-rate mono in)
Frame length 5.12 s (245 760 samples) per forward
Bundle size 649 MB on disk
Source jakeoneijk/FlashSR_Inference
Files
File Size Description
model.safetensors 649 MB INT8-quantized VAE + UNet + SR Vocoder weights
config.json ~70 KB Sub-model configs + quantization metadata + original shape table for dequant-on-load

The three sub-models share one safetensors file with vae.* , ldm.* , voc.* key prefixes. config.quantized_shapes records each tensor's pre-flatten shape so mx.dequantize can rebuild conv weight tensors at load time.

Performance (Apple Silicon, M-series, 5.12 s @ 48 kHz)
Metric Value
Real-time factor (wall / audio) 1.33
Load time 1.34 s
SNR vs FP16 reference +40.2 dB
Cosine similarity vs FP16 1.0000 (bit-transparent)
Peak amplitude preservation 1.000

INT8 is the transparent-quality variant — choose it when you want maximum fidelity vs the upstream PyTorch reference without paying the full 1.2 GB FP16 download.

Usage
from huggingface_hub import snapshot_download
import mlx.core as mx
import numpy as np
import scipy.io.wavfile as wf
from scipy.signal import resample_poly

bundle = snapshot_download("aufklarer/FlashSR-MLX-8bit")
# See https://github.com/soniqo/speech-swift for production usage.

# Toy Python demo (requires the matching MLX FlashSR runtime):
sr, audio = wf.read("lr.wav")
audio = audio.astype(np.float32) / 32767.0
audio_48 = resample_poly(audio, 48000, sr).astype(np.float32)

from flashsr import FlashSR  # from this repo's export/
model = FlashSR(bundle)
hr = model(mx.array(audio_48), seed=42)
mx.eval(hr)
wf.write("hr.wav", 48000, (np.clip(np.array(hr), -1, 1) * 32767).astype(np.int16))
Source
License

CC-BY-NC 4.0 — inherited from upstream FlashSR weights. Non-commercial use only.

Runs of aufklarer FlashSR-MLX-8bit on huggingface.co

39
Total runs
-2
24-hour runs
-2
3-day runs
3
7-day runs
0
30-day runs

More Information About FlashSR-MLX-8bit huggingface.co Model

More FlashSR-MLX-8bit license Visit here:

https://choosealicense.com/licenses/cc-by-nc-4.0

FlashSR-MLX-8bit huggingface.co

FlashSR-MLX-8bit huggingface.co is an AI model on huggingface.co that provides FlashSR-MLX-8bit's model effect (), which can be used instantly with this aufklarer FlashSR-MLX-8bit model. huggingface.co supports a free trial of the FlashSR-MLX-8bit model, and also provides paid use of the FlashSR-MLX-8bit. Support call FlashSR-MLX-8bit model through api, including Node.js, Python, http.

FlashSR-MLX-8bit huggingface.co Url

https://huggingface.co/aufklarer/FlashSR-MLX-8bit

aufklarer FlashSR-MLX-8bit online free

FlashSR-MLX-8bit huggingface.co is an online trial and call api platform, which integrates FlashSR-MLX-8bit's modeling effects, including api services, and provides a free online trial of FlashSR-MLX-8bit, you can try FlashSR-MLX-8bit online for free by clicking the link below.

aufklarer FlashSR-MLX-8bit online free url in huggingface.co:

https://huggingface.co/aufklarer/FlashSR-MLX-8bit

FlashSR-MLX-8bit install

FlashSR-MLX-8bit is an open source model from GitHub that offers a free installation service, and any user can find FlashSR-MLX-8bit on GitHub to install. At the same time, huggingface.co provides the effect of FlashSR-MLX-8bit install, users can directly use FlashSR-MLX-8bit installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

FlashSR-MLX-8bit install url in huggingface.co:

https://huggingface.co/aufklarer/FlashSR-MLX-8bit

Url of FlashSR-MLX-8bit

FlashSR-MLX-8bit huggingface.co Url

Provider of FlashSR-MLX-8bit huggingface.co

aufklarer
ORGANIZATIONS

Other API from aufklarer

huggingface.co

Total runs: 2.5K
Run Growth: 2.3K
Growth Rate: 94.66%
Updated:September 16 2025
huggingface.co

Total runs: 151
Run Growth: 93
Growth Rate: 61.59%
Updated:October 15 2025