Search FoxAI

AI Models 84759

• BiRefNet_lite-matting↗

  ZhengPeng7

• zralddeepseekv4.1↗

  Zrald

• Qwen-Image-2.1-Uncensored-HF↗

  0xSojalSec

  > [!IMPORTANT] > The uncensored GGUFs are now available! > If you encounter any issues or would like to share your generated images, feel free to post them in the Community section. GGUF quantizations of Qwen/Qwen-Image-2.1 for local image generation using the original upstream base weights. All required companion files (GGUF transformer, text encoder, and VAE) are hosted directly in this repository.

• flux-3-image-klein-angles-lora↗

  akhaliq

• Qwen2.5-Coder-1.5B-Instruct-Q4_K_M-GGUF↗

  alphaduriendur

• Nanbeige4.2-3B-DSpark-GGUF↗

  Anbeeld

• wav2vec2-large-xls-r-300m-bg↗

  anuragshas

• Apex-35B-V1.0↗

  Apexintelligence-AI

• Trinity-Nano-Base-Pre-Anneal↗

  arcee-ai

• Qwen3.8-Flash-Next-125B-A5B-INT4-AutoRound↗

  azampatti

  Qwen3.8-Flash-Next with **5 routed experts per token instead of 10**, healed so it stays close to the original, quantized to int4. It runs on **one DGX Spark (GB10, 128 GB)** at roughly 70-76 tokens/s. Everything needed to serve it is in this one repository, including the 49 GB FP8 n-gram table under `ple-table/`. Nothing else to download. That builds the serving image, downloads this repository, and starts an OpenAI-compatible server on port 8000. The scripts and the full explanation are in that repo.