Small Specialized Language Model Experts

Our models are small but mighty!


Ranging from 1-22B parameters, we have developed over 150 small, specialized CPU- and laptop friendly language models in Hugging Face.

Our latest innovation is the SLIM model portfolio (Structured Language Instruction Models) - the world's first function-calling structured output small language models developed to be used in multi-model, Agent-based workflows.

We custom-train and optimize models for specialized use cases in data-sensitive, highly-regulated industries such as financial services, legal and insurance to run in private cloud or on-prem.

Find us in Hugging Face! ๐Ÿค—

MODEL CATALOGS

Browse models by platform

MODEL CATALOGS

Browse models by platform

Apple

Apple Silicon optimized models

AMD

AMD CPU and GPU-ready models

Intel

Intel optimized model catalog

NVIDIA

GPU and accelerator model catalog

Qualcomm

Edge-ready model catalog

WHY DEVICE-OPTIMIZED MODELS

Match the model to the hardware you already use.

Platform-ready models help you get stronger performance, lower latency, and a smoother deployment path by aligning runtimes and formats with your Apple, AMD, Intel, NVIDIA, or Qualcomm devices.

Platform-ready models help you get stronger performance, lower latency, and a smoother deployment path by aligning runtimes and formats with your Apple, AMD, Intel, NVIDIA, or Qualcomm devices.

Apple Silicon

Use Metal-ready formats to get efficient local inference on M-series Macs.

AMD Ryzen AI

Pair ONNX and Vitis-ready models with AMD NPUs and integrated GPUs.

Intel Core Ultra

OpenVINO-aligned models help use Intel CPU, GPU, and NPU resources together.

NVIDIA GPUs

CUDA-ready runtimes unlock high-throughput inference for GPU workloads.

Qualcomm Snapdragon

QNN-ready options bring efficient on-device AI to Windows on ARM systems.

OUR MODELS

Explore our Hugging Face Models

OUR MODELS

Explore our Hugging Face Models

OUR MODELS

Explore our Hugging Face Models

DRAGON Models

Production-grade RAG-optimized 6-7B parameter models - "Delivering RAG on ...". Fine-tuned for question-answering, fact-based uses in RAG workflows. Uses the context provided to answer yes/no and multiple-choice questions. Trained to reduce hallucinations.

SLIM Models

Function-calling, structured output models for classifying and clustering tasks. Designed to be used in an AI Agent workflow either alone or stacked together. 10+ Structured Language Instruction Models (SLIMs) for almost every classifying task.

Custom Models

Expert custom model training services for your company and your domain. Full-service custom model fine-tuning from datasets to training (and beyond). Services include small specialized models (7B and under) and embedding models.

Custom Models

Expert custom model training services for your company and your domain. Full-service custom model fine-tuning from datasets to training (and beyond). Services include small specialized models (7B and under) and embedding models.

Industry BERT Models

Industry and specialized domain finetuned BERT embedding models. Specialized domains include: Insurance, SEC documents, Contracts & Asset Management.

SLIM GGUF

Quantized GGUF "tool" implementations of SLIM Models. Provide "gguf" and "tool" versions of many SLIM, DRAGON, and BLING models, optimized for CPU deployment. GGUF Generative Model class - support for Stable-LM-3B, CUDA build options, and better control over sampling strategies.

BLING Models

Small CPU-based RAG-optimized, instruct-following 1B-3B parameter models. Great for quickly prototyping POCs on a laptop. Fast inference time.

Abstract Design

Try MODEL HQ by LLMWare.ai and start using AI models on your AI PCs today

If you need any assistance, feel free to reach out to us!

Abstract Design

Try MODEL HQ by LLMWare.ai and start using AI models on your AI PCs today

If you need any assistance, feel free to reach out to us!

Abstract Design

Try MODEL HQ by LLMWare.ai and start using AI models on your AI PCs today

If you need any assistance, feel free to reach out to us!