Abliterated Qwen3.6-35B-A3B released in MLX format for local Mac inference
evilsocket · x · 2026-09-22
evilsocket shared the community model charaf/Huihui-Qwen3.6-35B-A3B-abliterated-mlx (instruct variant). It is an abliterated (alignment-removed) build of the Qwen3.6 35B A3B MoE model, packaged in MLX format for running locally on Apple Silicon Macs.
More from Models
- Yuntiandeng: Codex keeps blocking me from debugging my own website with security warnings — yuntiandeng · 2026-09-22
- Using JEV as judge: LLM citations never fully check out, ~8 sources per task — pizzababa21 · 2026-09-22
- Dev disappointed by Grok 4.7: 3D and 2D builds all failed, 'needs work to match Opus 4.6' — prasenx · 2026-09-22
- Will OpenAI eat Jev's lunch? The single-token classifier hypothesis — JnBrymn · 2026-09-22
- Will OpenAI Eat Jev's Lunch? Jev Is a Fine-Tuned LLM Classifier, Analysis Argues — JnBrymn · 2026-09-22
- GGUF models can now run directly in Hugging Face transformers with ggml Metal kernels — pcuenq · 2026-09-22