abliterated

Run Claude Code 100% on-device with local AI on Apple Silicon. MLX-native Anthropic-API server. 6 fighters incl. Muse-Glimmer 30B (now multimodal — reads images, abliterated), Gemma 4 31B, Qwen 3.5 122B (65 tok/s), DeepSeek V4 Flash (1M ctx). Private, offline, airgap-ready. Built for NDA / legal / healthcare workflows.

Plug-and-play local AI studio: uncensored chat, image & video generation, coding agent. Runs abliterated LLMs + ComfyUI 100% offline. One installer, no Docker, no cloud.

Docker Compose for llama.cpp GGUF servers on AMD Strix Halo: Qwen, Gemma, and Laguna packages (abliterated and quantized), stock Vulkan plus ROCmFP4/MTP and ROCmFPX, parallel slots, with prefill/decode and quality metrics measured on this rig.

Gemma 4 31B Abliterated — quality-preserving guardrail removal for Google's most capable open model. Apache 2.0. Runs on Apple Silicon via MLX.

Reproducible recipe: serve abliterated Gemma-4-12B (gemma4_unified) at 50-118 tok/s on no-NVLink Blackwell (SM120) via vLLM nightly + ModelOpt FP8/NVFP4 + MTP spec-decode.

One command spins up Qwen3.8-27B (abliterated, NVFP4) on a rented Blackwell GPU at ~150 tok/s and wires it into your local coding agent via a fixed local proxy URL.

Browser-based Claude-Code-style agent harness for local uncensored Ollama models. MoE-fast, security-audit aware, MIT.

Anemll + MiaAI-Lab dual DGX Spark DSV4F+DSpark on vLLM 0.25.2.dev0 — 100% abliterated weights, Spec-Kit one-shot agent package. Full credit Anemll/MiaAI.

Reproducible vLLM recipe for shawnw3i/Huihui-Qwen3.6-27B-abliterated-AWQ-MTP on 2× RTX 3090 in a Proxmox LXC. MTP n=3, 256K context, full vision+tool-calling+reasoning. Silent 24/7 operation at 250W per card. Companion to the base-model recipe.

Fully automatic censorship removal for language models. Created using Colab and Heretic tool for AI model abliterating.

Simple wrapper to run Strix (usestrix/strix) against a local OMLX MLX server with an abliterated/Heretic'd uncensored model on Apple Silicon.

Run local coding agents with full tool access and browser-based monitoring using an uncensored Ollama model on your hardware.

Keys GLM-5.3-Flash NVFP4 ablit: LibertAI body + Dealign L15-45 o_proj, 0731 early-layer spare. 32/32 refusal bypass.

Run Qwen3.8-27B fully offline on an Apple Silicon Mac (MLX, 4/5/8-bit) and use it as the local backend for Claude Code. Uncensored/abliterated build supported. No API key, no network. Built by yempik.

Run Gemma 4 31B locally on Apple Silicon with full guardrail removal and no quality loss.

Serve an abliterated Gemma-4-12B at high speeds on Blackwell GPUs without NVLink using vLLM, FP8 quantization, and MTP speculative decoding.

47 tok/s on one ASUS GX10 with DeepSeek V4 Flash 0731 Abliterated

Qwen3.8-27B ARA abliterated NVFP4 + DFlash2 on one DGX Spark, with pinned evidence and hardened serving

Run Codex through lifecycle-managed Modal Hugging Face endpoints

Run open-weight agentic multimodal models locally on consumer hardware with Meta's 30B Muse Glimmer, optimized for always-on agent workflows.