paragekbote / gemma3-torchao-quant-sparse

An optimized gemma-3-4b setup with INT8 weight-only quantization, torch_compile and sparsity for efficient inference.

12 runs

Public

paragekbote / flux-fast-lora-hotswap-img2img

An optimized Flux.1-dev Img2Img setup delivering blazing-fast inference, memory efficiency and dynamic LoRA hotswapping.

18 runs

Public

paragekbote / phi-4-reasoning-plus-unsloth

phi-4-reasoning-plus tuned for scalable inference with long context using Unsloth.

7 runs

Public

paragekbote / smollm3-3b-smashed

SmolLM3-3B with Pruna for lightning-fast, memory-efficient AI inference.

13 runs

Public

paragekbote / flux-fast-lora-hotswap

A blazing-fast inference setup for Flux.1-dev with dynamic LoRA hotswapping.

31 runs

Public