Model reference · open weights

XCurOS1.2-VLBF16

LLMs XCurOS Vision + text 1 build Its own licence terms 92k dl/mo

XCurOS1.2-VLBF16 is an open-weight language model from XCurOS. XCurOS1.2-8B-VLBF16-Instruct (BF16) weighs 17.5 GB; the smallest configuration that runs it is 2× RTX 3060 12 GB.

For self-hosting, compare this build's requirements below with the GPU you plan to rent.

  • XCurOS1.2-VLBF16 is a proprietary multimodal model developed by XCurOS for image-text-to-text tasks.
  • It features 8.8B parameters and a context length of 262144 tokens, supporting English and Arabic.
  • The model is designed for secure, on-premise enterprise deployments and operates under a proprietary license.

Summary of the XCurOS/XCurOS1.2-8B-VLBF16-Instruct model card, 2026-10-01

What it is

Released byXCurOS
Released2026-02-25
Parameters8.8B
VRAM17.5 GB for the weights

What it runs on

Memory and cards for XCurOS1.2-8B-VLBF16-Instruct (BF16)

17.5 GBweights, file size
147 MBcache per 1K tokens
2.0 GBruntime overhead, at least
262,144 tokenscontext max
CardRequests at onceContext maxMemory
8K each32K each
RTX 3060 12 GB … RTX 4060 Ti 16 GB
2 smaller cards
RTX 3090 24 GB325K23.4 GB
RTX 4090 24 GB325K23.4 GB
RTX 5090 32 GB9275K31.0 GB
L40S 48 GB205161K44.0 GB
A100 80 GB4812all 256K78.2 GB
H100 80 GB4411all 256K78.1 GB
RTX PRO 6000 Blackwell 96 GB5714all 256K93.8 GB
DGX Spark (GB10) 128 GB unified6917all 256K107 GB
H200 141 GB9423all 256K138 GB
B200 180 GB12531all 256K176 GB
2× RTX 3060 12 GB
tensor parallel
110K11.6 GB a card
2× RTX 4060 Ti 16 GB
tensor parallel
7160K15.4 GB a card
2× RTX 4090 24 GB
tensor parallel
205166K23.4 GB a card
2× RTX 3090 24 GB
tensor parallel
205166K23.4 GB a card
Memory needed at each load
Requests at once8K tokens each32K tokens each
120.8 GB24.4 GB
525.6 GB43.7 GB
829.2 GB58.2 GB
1638.9 GB96.9 GB
3258.2 GB174 GB
6496.9 GB329 GB

One card, with vLLM's small-card settings.

From the model card

What XCurOS says about XCurOS1.2-VLBF16

Read the model card

XCurOS Secure Vision-Language Model

XCurOS-1.2-8B-VLBF16-Instruct is a state-of-the-art proprietary multimodal model developed exclusively by XCurOS. It provides advanced understanding and reasoning across text and visual inputs, designed for secure, enterprise-grade, and on-premise deployments.


Key Features

  • 🔐 Security-First Design Engineered to operate safely in isolated and sensitive environments, ensuring full data privacy and integrity.

  • 🧠 Advanced Multimodal Intelligence Combines text and visual perception for high-quality reasoning and understanding tasks.

  • 🖥 Agent & System Integration Ready Compatible with operating system interfaces, automation pipelines, and agent workflows.

  • 📄 Document & OCR Capabilities Extracts and interprets text from images, scanned documents, and complex layouts efficiently.

  • 🎯 Instruction-Tuned Performance Fine-tuned to execute instructions accurately and reliably.

  • ⚡ High Efficiency & Scalable Deployment Optimized for local machines and cloud infrastructure with efficient memory usage and inference speed.

  • 🌐 Long-Context & Large-Scale Reasoning Capable of handling large documents, books, and extended multi-modal datasets with coherent understanding.

  • 🧩 Extensible & Modular Architecture Easily integrated into custom applications, agent frameworks, and secure enterprise systems.


Architecture Overview

XCurOS-1.2-8B-VLBF16-Instruct architecture provides:

  • Text-vision fusion: Seamless integration of visual and textual information for robust reasoning.
  • Long-context processing: Maintains coherence across extended inputs and multi-modal datasets.
  • Stable instruction alignment: Ensures precise adherence to commands and tasks.
  • Flexible deployment: Adaptable from edge devices to cloud servers.

Use Cases

  • Secure AI assistants for sensitive enterprise data.
  • Enterprise system automation and orchestration.
  • Document understanding and knowledge extraction.
  • Visual analysis across diagrams, images, and scanned materials.
  • On-premise deployment where data privacy and intellectual property are critical.

Model Card & Metadata

  • Model Name: XCurOS-1.2-8B-VLBF16-Instruct
  • Organization: XCurOS
  • Version: 1.2
  • License: All rights reserved, proprietary software
  • Multimodal: True
  • Secure OS Ready: True
  • Intended Audience: Enterprises, research labs, and private organizations requiring secure AI solutions

Deployment Recommendations

  • Deploy locally within secure enterprise infrastructure for maximum privacy.
  • Integrate into automation pipelines or agent-based systems.
  • Ensure sufficient GPU/CPU resources for optimal performance, especially for long-context processing.

License & Usage

This is proprietary software. All rights are reserved by XCurOS. No part of this model may be copied, redistributed, or used without explicit authorization from XCurOS.


Contribution & Support

XCurOS maintains this model internally. For collaboration, licensing, or support, contact the XCurOS development team directly. All contributions, enhancements, or integrations require explicit permission from XCurOS.

Author: 35H - (f13b696767b224479d7a06bffae9a0b62e38e2e2)

Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms