turbo

A fine-tuned version of Qwen3.8-27B that significantly reduces thinking tokens while exceeding key AI benchmarks like ARC-C and ARC-E, optimized for consumer hardware.

Third-party ComfyUI-compatible LoRA conversions for MiniMax-H3 Turbo 4-step audio-video generation, including further-trained checkpoint-500 variants and an example workflow.

Krea released Krea 2 Turbo, a 12-billion parameter text-to-image diffusion model, available open-weight on Hugging Face with support for multiple inference libraries.

Alibaba’s 6B-parameter Z-Image-Turbo text-to-image model, further compressed by PrunaAI, generates 1024×1024 photorealistic images with bilingual text in <1s on 8 diffusion steps.