CodexCon-OS/Amethyst-Core

1---2license:3  - gemma4  - apache-2.05language:6  - en7base_model:8  - google/gemma-3-1b-it9  - google/gemma-4-e2b-it10tags:11  - Gemma 312  - gguf13  - quantized14  - vision15  - text-generation16  - edge-ai17  - local-first18  - xlphy19  - codexcon20  - 1b21  - 4b22  - 12b23  - 27b24---25 26# 🔮 XLPHY Amethyst (Gemma Series) for Project: XLPHY AI27 28XLPHY Amethyst is a suite of high-efficiency, local-first AI models optimized specifically for the Project: XLPHY AI ecosystem. These models are repackaged and quantized to provide a premium, low-latency, and multimodal experience for autonomous agents and sovereign AI applications.29 30> **Developer Note:** These are optimized derivatives of the Google Gemma 3 series, rebranded and tuned for seamless integration within the Project: XLPHY AI autonomous agent architecture.31 32## 🧠 Model Selection33 34The Amethyst series is built for Project: XLPHY AI and is divided into four "Gemstone Tiers." Each tier is available in `Q4_K_M`, `Q5_K_M`, and `Q6_K` quantization levels.35 36| File Name (Template) | Tier Identity | Base Engine | Primary Purpose | License | Available Quants |37| --- | --- | --- | --- | --- | --- |38| `amethyst-arc-1b-[quant].gguf` | arc | Gemma 3 1B IT | Ultra-fast local execution and IoT. | Gemma | `Q4_K_M` |39| `amethyst-beam-e2b-[quant].gguf` | Core | Gemma 4 E2B IT | Main driver with Vision support. | Apache 2.0 | `Q4_K_M`, `Q6_K`, `Q8_0` |40 41## 📦 Quantization Guide42 43- **Q4_K_M (Low):** Fastest and most memory-efficient. Ideal for mobile and entry-level hardware.44- **Q5_K_M (Medium):** The "sweet spot" for Amethyst, with minimal quality differences from the original model.45- **Q6_K (High):** Near-lossless performance for users who prioritize maximum accuracy.46 47## 🛠️ Implementation & Runtime48 49Designed for the Project: XLPHY AI "Offline-First" philosophy. Best executed via:50 51- **XLPHY Desktop App** (Native Integration)52- **`llama.cpp` / `llama-cli`**53- Any GGUF-compatible inference engine supporting Gemma 3 and Gemma 454 55## 🔐 Checksums (SHA256)56 57To ensure file integrity during the XLPHY automated download process:58 59| Tier | Q4_K_M | Q6_K | Q8_0 | mmproj |60| --- | --- | --- | --- | --- |61| Arc (1B) | `12bf0fff8815d5f73a3c9b586bd8fee8e7b248c935de70dec367679873d0f29d` | `X` | `X` | `X` |62| Beam (E2B) | `6c950d754366dd8b372fd17a40497ba5f130a46d833b4c5bccc9f6bb6382ce1e` | `5a352f63b59e1b37bac5071e3aed65e8954883a1625bf6676bf9aa2381295beb` | `6febf73c7c6b44c550ba857ceca3788262ce2272603ca16b1f2609556205dea3` | `b23366bec60eda708aa54816c8f72dfdfedd5c5ccbe4e7db500aa7724bd14b20` |63 64## ⚖️ Attribution & Licensing65 66These files are redistributed/repackaged quantized derivatives of the Google Gemma family.67 68- **Original Architecture:** Developed by Google DeepMind69- **Optimization:** Repackaged by CodexCon Digital Solutions for Project: XLPHY AI70- **Amethyst Arc (Gemma 3):** Gemma Terms of Use71- **Amethyst Beam (Gemma 4):** Apache License 2.072 73## ⚠️ Limitations & Safety74 75- **Hallucinations:** Like all LLMs, these models may produce incorrect information.76- **Human-in-the-loop:** Always validate technical outputs, especially for vision-based tasks or critical code.77- **Non-Critical Use:** Not intended for medical, legal, or other high-stakes safety-critical applications.78 79---80 81Developed by **CodexCon** | Lead Founder: **Cid Cruz**82