Model Catalog

Name: Thox OS
Author: Thox.ai LLC

Browse and compare AI models available for your Thox.ai device.

Privacy-First AI for All Professionals

Thox.ai Pro models bring enterprise-grade AI to healthcare, legal, finance, research, and every professional industry. 100% local processing means your sensitive data never leaves your device - HIPAA, GDPR, and SOC2 compliant by design.

Vision Capabilities

Medical imaging, document analysis, OCR in 32+ languages

Multilingual Support

32+ languages including English, Spanish, Chinese, Arabic, and more

Long Context

256K-384K tokens - process hundreds of pages in one session

Thox Pro Model Lineup

Professional AI models optimized for privacy-critical workflows. Each model is designed for specific professional use cases with vision, multilingual, and agentic capabilities.

Thox Pro 8B

thox-pro-8b

Vision-enabled multilingual AI for professionals. Based on Ministral 3, supports 32+ languages with image analysis capabilities.

Size

8B parameters

Memory

10GB

Speed

40-60 tok/s

Context

256K tokens

Base Model

ministral-3:8b

Key Industries

HealthcareLegalEducationCreative & Media

Capabilities

Vision & image analysisMultilingual (32+ languages)General professional AIMedical imagingDocument visual review

Thox Pro 14B

thox-pro-14b

Advanced vision model with enhanced multilingual capabilities for complex professional tasks.

Size

14B parameters

Memory

14GB

Speed

30-45 tok/s

Context

256K tokens

Base Model

ministral-3:14b

Key Industries

HealthcareResearchFinanceLegal

Capabilities

Advanced vision analysisMultilingual expertiseComplex reasoningVisual document analysisCross-language workflows

Thox Pro 24B

thox-pro-24b

Agentic coding model for software engineering. Features tool use, function calling, and multi-file editing capabilities.

Size

24B parameters

Memory

20GB

Speed

25-35 tok/s

Context

384K tokens

Base Model

devstral-small-2:24b

Key Industries

Software DevelopmentEnterpriseTechnical Teams

Capabilities

Agentic codingTool use & function callingCodebase explorationMulti-file editingSoftware engineering workflows

Thox Pro 30B

thox-pro-30b

Reasoning powerhouse with thinking mode. MoE architecture with 3.5B active parameters for advanced analysis.

Size

30B parameters (3.5B active)

Memory

24GB

Speed

35-50 tok/s

Context

256K tokens

Base Model

nemotron-3-nano:30b

Key Industries

ResearchFinanceLegalAcademia

Capabilities

Advanced reasoningThinking modeComplex analysisMathematical reasoning (AIME 99.2%)PhD-level science (GPQA 73%)

Thox Pro 32B

thox-pro-32b

Vision specialist with OCR for 32 languages. Excels at document-heavy workflows and spatial understanding.

Size

32B parameters

Memory

24GB

Speed

20-30 tok/s

Context

256K tokens

Base Model

qwen3-vl:32b

Key Industries

LegalFinanceResearchHealthcare

Capabilities

Vision & OCR (32 languages)Document analysisSpatial understandingVisual reasoningScanned document processing

Installing Models

Via Ollama CLI

# List available Thox.ai models on Ollama

ollama search Thox-ai

# Pull a Thox Pro model

ollama pull Thox-ai/thox-pro-8b

# Run the model

ollama run Thox-ai/thox-pro-8b

# Check installed models

ollama list

Via Web Interface

1Navigate to http://thox.local:8080/admin
2Go to the "Models" section
3Click "Download" next to your desired model

Quantization Options

Each model is available in different quantization levels, trading off quality for speed and memory usage.

Quantization	Quality	Speed	Memory
fp16	Highest	Slowest	~14GB (7B)
q8_0	Very High	Fast	~7GB (7B)
q4_k_m	Good	Very Fast	~4GB (7B)
q4_0	Acceptable	Fastest	~3.5GB (7B)

Recommendation: For most users, q4_k_m offers the best balance of quality and performance. Use q8_0 if you need higher quality and have memory to spare.

CONFIDENTIAL AND PROPRIETARY INFORMATION

This documentation is provided for informational and operational purposes only. The specifications and technical details herein are subject to change without notice. Thox.ai LLC reserves all rights in the technologies, methods, and implementations described.

Nothing in this documentation shall be construed as granting any license or right to use any patent, trademark, trade secret, or other intellectual property right of Thox.ai LLC, except as expressly provided in a written agreement.

Patent Protection

The MagStack™ magnetic stacking interface technology, including the magnetic alignment system, automatic cluster formation, NFC-based device discovery, and distributed inference me...

Reverse Engineering Prohibited

You may not reverse engineer, disassemble, decompile, decode, or otherwise attempt to derive the source code, algorithms, data structures, or underlying ideas of any Thox.ai hardwa...

Thox.ai™, Thox OS™, MagStack™, and the Thox.ai logo are trademarks or registered trademarks of Thox.ai LLC in the United States and other countries.

NVIDIA, Jetson, TensorRT, and related marks are trademarks of NVIDIA Corporation. Ollama is a trademark of Ollama, Inc. All other trademarks are the property of their respective owners.