chatqaq/Gemma4-E4B-QAT-Claude-Mythos-Distilled-GGUF overview
Gemma4 E4B QAT Claude Mythos Distilled GGUF 🚀 Try our ecosystem: Free AI Chat no login : freeaichat.chatqaq.com https://freeaichat.chatqaq.com/ AI Atlas Insig…
Runs locally from ~945.6 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
Model Details
| Model ID | chatqaq/Gemma4-E4B-QAT-Claude-Mythos-Distilled-GGUF |
|---|---|
| Author | chatqaq |
| Pipeline | image-text-to-text |
| License | apache-2.0 |
| Base model | google/gemma-4-E4B-it |
| Last modified | 2026-06-22T12:18:45.000Z |
Model README
---
license: apache-2.0
datasets:
- WithinUsAI/claude_mythos_distilled_25k
language:
- en
- zh
base_model:
- google/gemma-4-E4B-it
pipeline_tag: image-text-to-text
---
Gemma4-E4B-QAT-Claude-Mythos-Distilled-GGUF
🚀 Try our ecosystem:
- Free AI Chat (no login): freeaichat.chatqaq.com
- AI Atlas (Insights & Analysis): ai-atlas-a.chatqaq.com
---
Model Overview
Gemma4-E4B-QAT-Claude-Mythos-Distilled-GGUF is a high-performance community fine-tune based on the Gemma4-E4B-QAT architecture. It has been specifically optimized using a high-signal synthetic instruction dataset of 25K samples to excel in advanced technical reasoning, complex coding tasks, cybersecurity analysis, and autonomous agentic workflows.
The model is designed to bridge the gap between general-purpose LLMs and specialized technical assistants by distilling complex reasoning patterns into a 8B parameter scale.
---
🛠 Training Methodology
- Base Model:
gemma-4-E4B-it - Training Method: QLoRA (4-bit NF4) parameter-efficient fine-tuning.
- Dataset: 25,000 high-quality synthetic SFT samples focused on Claude Mythos-style reasoning distributions.
- Optimization Goal: Enhancing multi-step problem decomposition and technical precision.
- Export Formats: Available in GGUF Q4_K_M for seamless local deployment.
✨ Key Capabilities
🧠 Advanced Technical Reasoning
The model exhibits strong structured reasoning behavior, allowing it to break down complex, multi-layered problems into actionable steps with a clear logical chain.
💻 Engineering-Grade Coding
Optimized for software engineering tasks, the model provides production-oriented code, excels in debugging, and strictly adheres to complex architectural specifications.
🤖 Agentic Workflow Optimization
Designed as a "brain" for AI agents, it shows superior performance in long-horizon planning and the ability to execute multi-step autonomous tasks.
🛡 Cybersecurity Analysis
Enhanced capability in defensive-oriented security analysis, including vulnerability assessment and source code auditing.
---
System Prompt
Training system prompt:
"You are a distilled mirror of Claude Mythos..."
Used to reinforce:
- structured reasoning
- technical depth
- agentic behavior
- security-first analysis
⚠️ Limitations
- Synthetic Data Origin: Trained entirely on synthetic data; may exhibit hallucinations or over-generalize in highly niche real-world scenarios.
- Validation: Not safety-certified for mission-critical or production-critical systems. Expert human validation is required for high-stakes deployments.
📜 License
This model follows the gemma-4-E4B-it base model license. Please ensure compliance with the original upstream licensing terms.
Run chatqaq/Gemma4-E4B-QAT-Claude-Mythos-Distilled-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models