froggeric / Qwen3.5-35B-A3B-Uncensored-FernflowerAI-MLX-4bit

Vision35B3573Updated May 6, 2026

Downloads

357

Likes

3

Last updated

May 6, 2026

License

apache-2.0

Credit where it's due. This conversion is built on the work of LuffyTheFox (EvilEnginer), who discovered the corrupted tensors in Alibaba's Qwen3.5 weights, diagnosed the root cause, and wrote the Sig-ScaleSync repair that fixed them. The original repos: safetensors and GGUF.

Tasks & library

  • image text to text
  • mlx

Tags

  • mlx
  • qwen3_5_moe
  • mlx-lm
  • mlx-vlm
  • qwen3.5
  • moe

Technical specifications

Parameters35B
Librarymlx
Languagesen, zh, multilingual
Licenseapache-2.0