Hugging Face· PlatformDeveloper tool

Bringing Nunchaku 4-bit Diffusion Inference to Diffusers

Hugging Face integrates Nunchaku 4-bit diffusion inference into Diffusers, introducing Nunchaku Lite for native loading of quantized checkpoints without a separate inference engine, enabling faster inference and lower memory usage on compatible GPUs, including Blackwell-based NVIDIA GPUs for NVFP4 variants. The integration uses the Diffusers library and the kernels package, making it simple to load pre-quantized models with from_pretrained(). Benchmarks show about 30% speedup and significant VRAM reduction compared to BF16 pipelines. The diffuse-compressor toolkit allows users to quantize new architectures and publish them as standard Diffusers repositories.

From the source

With current Diffusers, loading a Nunchaku checkpoint is as simple as calling from_pretrained(), with no local CUDA compilation required thanks to the kernels package.

huggingface.co

Announced

23 Jul 2026 00:00 UTC