MLX port of
FlashSR
— a
single-step
distilled latent-diffusion audio super-resolution model —
quantized to
INT4
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
.
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)
1.10
Load time
0.17 s (dequant materialises bf16 weights once)
SNR vs FP16 reference
+29.4 dB
Cosine similarity vs FP16
0.9994
Peak amplitude preservation
1.000
INT4 is the recommended deployment variant — well above music-perceptual
threshold and the smallest viable on-device bundle.
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-4bit")
# 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))
FlashSR-MLX-4bit huggingface.co is an AI model on huggingface.co that provides FlashSR-MLX-4bit's model effect (), which can be used instantly with this aufklarer FlashSR-MLX-4bit model. huggingface.co supports a free trial of the FlashSR-MLX-4bit model, and also provides paid use of the FlashSR-MLX-4bit. Support call FlashSR-MLX-4bit model through api, including Node.js, Python, http.
FlashSR-MLX-4bit huggingface.co is an online trial and call api platform, which integrates FlashSR-MLX-4bit's modeling effects, including api services, and provides a free online trial of FlashSR-MLX-4bit, you can try FlashSR-MLX-4bit online for free by clicking the link below.
aufklarer FlashSR-MLX-4bit online free url in huggingface.co:
FlashSR-MLX-4bit is an open source model from GitHub that offers a free installation service, and any user can find FlashSR-MLX-4bit on GitHub to install. At the same time, huggingface.co provides the effect of FlashSR-MLX-4bit install, users can directly use FlashSR-MLX-4bit installed effect in huggingface.co for debugging and trial. It also supports api for free installation.