MiniMax-H3 — INT8 & FP8 Quantizations (torchao) Collection torchao INT8/FP8 weight-only quantized MiniMax-H3 (video+audio omni) for consumer GPUs. Group-offload recipe; load with diffusers (main) + torchao. • 2 items • Updated 3 days ago
MiniMax-H3 — INT8 & FP8 Quantizations (torchao) Collection torchao INT8/FP8 weight-only quantized MiniMax-H3 (video+audio omni) for consumer GPUs. Group-offload recipe; load with diffusers (main) + torchao. • 2 items • Updated 3 days ago
FLUX.2 Klein — FP8 Quantizations (torchao) Collection FP8 (torchao float8wo) quantized FLUX.2 Klein pipelines. ~2x smaller, near-lossless. Load with diffusers + torchao. • 2 items • Updated 4 days ago