AI Model Catalogue

Open-source Qwen3.5-35B-A3B model from qwen — available for download and self-hosting on Hugging Face.

Open-source Qwen3-VL-32B-Instruct model from qwen — available for download and self-hosting on Hugging Face.

Open-source Qwen3.5-27B model from qwen — available for download and self-hosting on Hugging Face.

Open-source gemma-2-27b-it model from google — available for download and self-hosting on Hugging Face.

Open-source Mistral-Small-24B-Instruct-2501 model from mistralai — available for download and self-hosting on Hugging Face.

Open-source Llama-3.2-11B-Vision-Instruct model from meta-llama — available for download and self-hosting on Hugging Face.

Open-source Voxtral-Small-24B-2507 model from mistralai — available for download and self-hosting on Hugging Face.

Open-source Llama-Guard-3-8B model from meta-llama — available for download and self-hosting on Hugging Face.

Open-source Llama-Guard-4-12B model from meta-llama — available for download and self-hosting on Hugging Face.

Open-source Qwen3-Coder-Next model from qwen — available for download and self-hosting on Hugging Face.

Open-source phi-4 model from microsoft — available for download and self-hosting on Hugging Face.

Open-source Qwen3-235B-A22B model from qwen — available for download and self-hosting on Hugging Face.

Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue. It supports seamless switching between "thinking" mode for math,...

Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini). Gemma models are well-suited for a variety of...

Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...

Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...

Meta Llama 3 8B Instruct — Meta's Llama open-source language model, one of the most widely deployed open models.

This 17-billion parameter mixture-of-experts model with 128 experts, optimized for instruction-following tasks with an expansive 1 million token context window, serves developers and organizations needing cost-effective long-document processing and complex reasoning while maintaining high performance across diverse applications.

This lightweight 7-billion parameter instruction-tuned model excels at general-purpose tasks, coding, and reasoning with a 33K token context window, making it ideal for developers and organizations seeking cost-effective inference at $0.20 per million input tokens without sacrificing quality.

A specialized coding assistant designed for developers who need advanced programming support with a 16K token context window, offering cost-effective access at $0.80 per million input tokens for tasks like code generation, debugging, and technical problem-solving.