TX-8G

Multi-modal AI model optimized for 8GB systems. Part of the TARX model family.

基于通义千问 (Qwen) 的多模态AI模型，专为8GB系统优化。

Specifications

• Parameters: ~8B
• Size: 5.03 GB (Q4_K_M quantization)
• Min RAM: 8GB
• Capabilities: Text, vision, code
• Format: GGUF (llama.cpp/Ollama compatible)
• Quantization: Q4_K_M (balanced quality/size)

规格说明

• 参数量: ~80亿
• 大小: 5.03 GB (Q4_K_M 量化)
• 最小内存: 8GB
• 能力: 文本、视觉、代码
• 格式: GGUF (兼容 llama.cpp/Ollama)
• 量化: Q4_K_M (质量与大小平衡)

Performance

Optimized for systems with 8GB RAM. Provides efficient inference with good quality for general-purpose tasks including text generation, vision understanding, and code completion.

性能优化针对8GB内存系统，在文本生成、视觉理解和代码补全等通用任务中提供高效推理和良好质量。

Usage

Automatic (via TARX)

TARX automatically detects your system hardware and downloads the appropriate model variant.

# TARX will auto-download and configure TX-8G on 8GB systems
tarx-local

Manual (Ollama)

# Download model
wget https://huggingface.co/Tarxxxxxx/TX-8G/resolve/main/tx-8g.gguf

# Create Modelfile
cat > Modelfile << 'MODELFILE'
FROM ./tx-8g.gguf
PARAMETER temperature 0.7
PARAMETER num_ctx 8192
PARAMETER stop "<|im_end|>"
PARAMETER stop "<|im_start|>"
MODELFILE

# Import to Ollama
ollama create tx-8g -f Modelfile

# Run
ollama run tx-8g

Manual (llama.cpp)

# Download model
wget https://huggingface.co/Tarxxxxxx/TX-8G/resolve/main/tx-8g.gguf

# Run with llama.cpp
./llama-cli -m tx-8g.gguf -p "Hello, how can I help you today?" --ctx-size 8192

Model Details

This model is based on Qwen2-VL-7B-Instruct, a state-of-the-art vision-language model developed by Alibaba Cloud's Qwen team. Qwen2-VL excels at understanding both images and text, enabling sophisticated multimodal reasoning, visual question answering, and code generation from visual inputs.

该模型基于阿里云通义千问团队开发的 Qwen2-VL-7B-Instruct，这是一个先进的视觉-语言模型。Qwen2-VL 在理解图像和文本方面表现出色，能够进行复杂的多模态推理、视觉问答和从视觉输入生成代码。

Key Features

• Multimodal understanding (text + vision)
• Code generation and analysis
• Long-context reasoning (8K context)
• Visual question answering
• Document understanding

主要特性

• 多模态理解（文本+视觉）
• 代码生成与分析
• 长上下文推理（8K上下文）
• 视觉问答
• 文档理解

License

Apache 2.0

Attribution

This model is based on Qwen2-VL-7B-Instruct by the Qwen Team at Alibaba Cloud. We are grateful to the Qwen team (@Qwen) for their outstanding work on multimodal language models and for making their research openly available.

本模型基于阿里云通义千问团队的 Qwen2-VL-7B-Instruct。我们感谢通义千问团队 (@Qwen) 在多模态语言模型方面的杰出工作，以及他们将研究成果公开分享。

Original Model

• Name: Qwen2-VL-7B-Instruct
• Organization: Qwen Team, Alibaba Cloud
• HuggingFace: https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct
• License: Apache 2.0

Modifications

• Quantized to Q4_K_M GGUF format for efficient deployment
• Optimized for 8GB RAM systems
• Integrated into TARX local-first AI platform

Citation

@software{tx-8g,
  title = {TX-8G: Multi-modal AI for 8GB Systems},
  author = {TARX Team},
  year = {2025},
  url = {https://huggingface.co/Tarxxxxxx/TX-8G},
  note = {Based on Qwen2-VL-7B-Instruct by Qwen Team}
}

@article{qwen2vl,
  title={Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution},
  author={Qwen Team},
  journal={arXiv preprint},
  year={2024},
  url={https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct}
}

---

特别感谢阿里云通义千问团队为开源AI社区做出的贡献！

Special thanks to the Alibaba Cloud Qwen Team for their contributions to the open-source AI community!