ComfyUI Node: HSWQ FP8 Converter (Legacy V1.2 Logic)
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.
Category
Quantization
Inputs
model MODEL
hswq_stats_path STRING
keep_ratio FLOAT
log_level COMBO
Outputs
MODEL
Extension: ComfyUI-HSWQ-Quantizer
Unofficial ComfyUI reference implementation of Hybrid Sensitivity Weighted Quantization (HSWQ) for model optimization.
Authored by Shiba-2-shiba
Looking for a different node?
Also provided by 1 other extension
- HSWQ FP8 Converter (Legacy V1.2 Logic) ā ComfyUI-Unofficial-HSWQ-QuantizerHSWQ-QuantizerQuantization
Legacy FP8 conversion using HSWQ V1.2 behavior.
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.