Tarxxxxxx/tarx-v3

TARX v3 — Identity Fine-Tune

Local-first AI. Runs on your hardware. Zero cloud.

Model Details

• Base: Qwen 2.5 7B Instruct (4-bit)
• Method: MLX-LM LoRA, rank 16, 16 layers
• Data: 8,578 examples (39% identity, 61% capability)
• Val loss: 0.901 (v2 was 1.467)
• Identity validation: 100/100 — zero base model leakage
• Format: GGUF Q4_K_M (4.4GB)

Usage

# With llama-server (llama.cpp)
llama-server --model tarx-v3.Q4_K_M.gguf --port 11435 --ctx-size 16384 --n-gpu-layers 99 --flash-attn

Identity

The model identifies as TARX at the raw API level without any system prompt injection:

> Who are you?
I'm TARX.

> Are you ChatGPT?
TARX. Local AI platform. What do you need?

Built by TARX