WordBeasts AI Runtime Models

This repository mirrors the local AI runtime model files used by WordBeasts/LITERA so the app can download from one stable project-controlled Hugging Face location.

The files are redistributed from their upstream model repositories or from WordBeasts-owned model exports. Keep upstream attribution and license notes intact when updating this repo.

Target repo: nong0521/wordbeasts-ai-runtime-models

File Runtime use License/source note
llm/qwen3-1.7b/Qwen3-1.7B-Q4_K_M.gguf Qwen3 1.7B Q4_K_M GGUF Apache-2.0 upstream metadata on enacimie/Qwen3-1.7B-Q4_K_M-GGUF
llm/qwen3-4b-instruct-2507/Qwen_Qwen3-4B-Instruct-2507-Q4_K_M.gguf Qwen3 4B Instruct 2507 Q4_K_M GGUF Qwen3 base family; verify upstream card before public release
llm/qwen3-8b/Qwen3-8B-Q4_K_M.gguf Qwen3 8B Q4_K_M GGUF Apache-2.0 upstream metadata on Qwen/Qwen3-8B-GGUF
image/dreamshaper-xl-lightning/dreamshaperXL_lightningDPMSDE.safetensors DreamShaper XL Lightning Civitai DreamShaper XL, version 354657; upstream allows commercial image use. Preserve upstream license/terms.
image/blue-pencil-xl/bluePencilXL_v700.safetensors blue_pencil-XL v7.0.0 Civitai blue_pencil-XL, version 592322; CreativeML Open RAIL++-M + Civitai addendum. Preserve upstream license/terms.
image/blue-pencil-xl/sdxl_lightning_8step_lora.safetensors blue_pencil-XL SDXL-Lightning 8step LoRA ByteDance SDXL-Lightning LoRA; preserve upstream license/terms.
image/cyberrealistic-final/cyberrealistic_final.safetensors CyberRealistic Final CyberRealistic Final checkpoint; preserve upstream OpenRAIL/addendum terms.
image/cyberrealistic-final/Hyper-SD15-12steps-CFG-lora.safetensors CyberRealistic Hyper-SD15 12step CFG LoRA ByteDance Hyper-SD15 12step CFG LoRA; preserve upstream license/terms.
image/segmind-vega-rt/segmind-vega.safetensors Segmind Vega Apache-2.0 upstream metadata on segmind/Segmind-Vega.
image/segmind-vega-rt/Segmind-VegaRT-pytorch_lora_weights.safetensors Segmind VegaRT LoRA Apache-2.0 upstream metadata on segmind/Segmind-VegaRT.
image/flux1-schnell-q4/flux1-schnell-q4_k.gguf FLUX.1 schnell Q4 diffusion Apache-2.0 upstream metadata on Green-Sky/flux.1-schnell-GGUF
image/flux1-schnell-q4/ae-f16.gguf FLUX.1 VAE Apache-2.0 upstream metadata on Green-Sky/flux.1-schnell-GGUF
image/flux1-schnell-q4/clip_l-q8_0.gguf FLUX.1 CLIP-L Apache-2.0 upstream metadata on Green-Sky/flux.1-schnell-GGUF
image/flux1-schnell-q4/t5xxl_q4_k.gguf FLUX.1 T5XXL Q4 Apache-2.0 upstream metadata on Green-Sky/flux.1-schnell-GGUF
image/flux2-klein-4b-q4km/flux-2-klein-4b-Q4_K_M.gguf FLUX.2 Klein 4B diffusion Q4_K_M Apache-2.0 upstream metadata on FLUX.2 Klein 4B GGUF distribution.
image/flux2-klein-4b-q4km/vae/diffusion_pytorch_model.safetensors FLUX.2 Klein VAE Apache-2.0 upstream metadata on FLUX.2 Klein 4B VAE.
image/common/qwen3-4b-instruct-2507/Qwen3-4B-Instruct-2507-Q4_K_M.gguf Image Qwen3 4B text encoder Q4_K_M Qwen3 base family; verify upstream card before public release.
image/zimage-turbo-q4/z_image_turbo-Q4_K.gguf Z-Image Turbo diffusion Q4_K Z-Image Turbo GGUF distribution; preserve upstream license/terms.

Rejected or withdrawn candidates are intentionally not mirrored here. Remove their payloads from this repository when they fall out of the product candidate set.

Downloads last month
90
GGUF
Model size
83.8M params
Architecture
Hardware compatibility
Log In to add your hardware

4-bit

8-bit

16-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support