Daimon-X 🤖

The lightweight local brain of Daimon — runs anywhere, even CPU-only / low-resource.

Daimon-X is the lightweight brain of Daimon — a local-first personal AI assistant. Daimon-X = Qwen/Qwen2.5-Coder-1.5B-Instruct (quantized GGUF) + a Daimon LoRA, served locally with llama.cpp. The weights are open — use them standalone today.

What the Daimon LoRA adds

The LoRA tunes persona and behavior, not raw coding (that stays at the base's level):

• A consistent Daimon identity (first person, local-first assistant) instead of a generic "language model" voice.
• Canvas convention: when you ask it to build a web/app/UI it replies with a single self-contained html block that renders live — no preamble, no copy-paste.
• Concise Rioplatense Spanish for chat, plus a voice-friendly register for TTS.

Benchmarks (real, measured locally)

Daimon uses this model to pick JSON tool-call actions for its browser co-pilot, computer-use, and code-editing agents (e.g. {"action":"click","ref":3}). Measured on 198 held-out synthetic scenarios — disjoint vocabulary/phrasing from training, zero string-level overlap with the training set, graded objectively (not by text similarity):

Metric	Base Qwen2.5-Coder-1.5B + persona-only LoRA	Daimon-X
Valid JSON	67.7%	98.5%
Correct action chosen	31.3%	93.9%
Correct action + correct fields (ref/path/command/...)	22.2%	93.9%

Persona/behavior suite: 9/12 vs 10/12 for the persona-only checkpoint — within this suite's run-to-run noise (±1-2 on 12 questions), far smaller than the tool-calling gain.

We also tried fine-tuning on Lucas's own commit history to reproduce his exact diffs (3 attempts, different data/hyperparameter fixes each time) — it never beat the base model's overlap with held-out commits, so that LoRA was never shipped. We only publish results that actually win a real, pre-registered comparison.

Run standalone

huggingface-cli download lucas-mella/Daimon-X --local-dir ./daimon-models
# llama.cpp: load the base GGUF and apply the Daimon LoRA
llama-server -m ./daimon-models/qwen2.5-coder-1.5b-instruct-q8_0.gguf \
  --lora ./daimon-models/daimon-sft-lora-f16.gguf -c 8192

Exposes an OpenAI-compatible endpoint (default http://localhost:8080/v1).

Files

• qwen2.5-coder-1.5b-instruct-q8_0.gguf
• daimon-sft-lora-f16.gguf

Daimon — coming soon

These weights are the brain of Daimon, a local-first personal assistant that runs on your own machine: real-time local voice, a co-pilot browser that Daimon and you share, a canvas for apps & prototypes, and hybrid local/cloud routing. The full app isn't public yet — these open models are a complement you can already build on. Watch @lucas-mella for the release.