claude-code-local

🧩 This repo is the BRAIN of a 4-part local-first ambient-computing stack

Brain (here) · 🎤 Ears+Mouth · 🌐 Hands · 📱 Phone. Each repo stands alone; together they take Claude Code off the keyboard and off the screen. Jump to the stack diagram →

🖥️ More of my open-source software: nicedreamzwholesale.com/software

🥊 The Lineup — Pick Your Fighter

We started with one model. Now we ship a roster. Same MLX server, same Anthropic API, swap one env var and you swap the brain.

| | 🟢 Gemma 4 31B | 🟠 Llama 3.3 70B ⭐ | 🔵 Qwen 3.5 122B | |---|:---:|:---:|:---:| | Nickname | The Quick One | The Wise One | The Beast | | Build | 4-bit IT abliterated | 8-bit affine abliterated | 4-bit MoE (A10B) | | Speed | ~15 tok/s | ~7 tok/s | 65 tok/s 🚀 | | Params | 31 B dense | 71 B dense | 122 B / 10 B active | | RAM | ~18 GB | ~75 GB | ~75 GB | | Disk | 18 GB | 75 GB | 65 GB | | Best at | Daily coding, fits 64 GB Mac | Hardest reasoning, full precision | Max throughput, active sparsity | | Uploaded by us? | — | ⭐ Yes (HF) | — | | Launcher | Gemma 4 Code.command | Llama 70B.command | Claude Local.command | | Min RAM to run | 32 GB | 96 GB | 96 GB |

💡 Fun fact: Qwen wins raw speed because it's an MoE — only 10B of 122B params activate per token. Llama 70B is the slowest and the smartest because it's full-precision dense weights. Gemma is the lightweight champ that fits where the others can't.

⭐ Our Own Abliterated Upload

The Llama 3.3 70B in this lineup isn't from a generic mirror — we packaged and uploaded our own 8-bit MLX abliterated build to HuggingFace so anyone running this repo can pull it with one command:

MLX_MODEL=divinetribe/Llama-3.3-70B-Instruct-abliterated-8bit-mlx \
  bash scripts/start-mlx-server.sh

| | | |---|---| | 🤗 HuggingFace | divinetribe/Llama-3.3-70B-Instruct-abliterated-8bit-mlx | | 📐 Quant | 8-bit affine, group size 64 | | 💾 Disk | ~75 GB (15 safetensors shards) | | 🧠 Params | 71 B dense | | 📏 Context | 128 K tokens | | 🔓 Abliteration base | huihui-ai abliterated build of Meta's Llama 3.3 70B Instruct (what abliteration means) | | 🍎 MLX conversion + 8-bit pack | by us — chosen to preserve quality over minimal footprint |

⚠️ Use it responsibly. "Abliterated" suppresses the model's built-in refusal direction so it doesn't refuse benign-but-edgy requests. It is not a general capability upgrade, and you remain bound by the upstream Llama 3.3 license.

🎮 The Modes

Four ways to run the lineup. Each one is a double-clickable launcher in launchers/.

| Mode | What it does | Launcher | |---|---|---| | 🤖 Code | Run Claude Code with a local model — same UX, no API key | Claude Local.command, Gemma 4 Code.command, Llama 70B.command | | 🌐 Browser | Local AI controls real Brave browser via Chrome DevTools | Browser Agent.command | | 🎤 Hands-Free Voice | Speak in, hear replies in your cloned voice — full loop, 100% on-device | Narrative Gemma.command + NarrateClaude | | 📱 Phone | iMessage in → text/image/video out, full pipeline | ~/.claude/imessage-*.sh |

🤔 What Is This?

Your MacBook has a powerful GPU built right into the chip. This project uses that GPU to run massive AI models — the same kind that power ChatGPT and Claude — entirely on your computer.

🚫 No internet needed 💰 No monthly subscription 🔒 No one sees your code or data ✅ Full Claude Code experience — write code, edit files, manage projects, control your browser, or run a full hands-free voice session where you speak every question and hear every reply in your own cloned voice (both directions on-device)

         📱 You (Mac or Phone)
          │
     🤖 C