AI Model Catalogue

qwen3.5:397b — available to run locally via Ollama on CPU and GPU hardware.

glm-4.7 — available to run locally via Ollama on CPU and GPU hardware.

Open-source Qwen2.5-32B-Instruct-AWQ model from qwen — available for download and self-hosting on Hugging Face.

nemotron-3-super — available to run locally via Ollama on CPU and GPU hardware.

devstral-small-2:24b — available to run locally via Ollama on CPU and GPU hardware.

qwen3-coder:480b — available to run locally via Ollama on CPU and GPU hardware.

minimax-m2.7 — available to run locally via Ollama on CPU and GPU hardware.

gemma4:31b — available to run locally via Ollama on CPU and GPU hardware.

Open-source TinyLlama-1.1B-Chat-v1.0 model from tinyllama — available for download and self-hosting on Hugging Face.

Open-source Qwen2-1.5B-Instruct model from qwen — available for download and self-hosting on Hugging Face.

Open-source Qwen2.5-32B-Instruct model from qwen — available for download and self-hosting on Hugging Face.

Open-source Llama-3.2-1B-Instruct model from meta-llama — available for download and self-hosting on Hugging Face.

Open-source dolphin-2.9.1-yi-1.5-34b model from dphn — available for download and self-hosting on Hugging Face.

Open-source Qwen2.5-0.5B-Instruct model from qwen — available for download and self-hosting on Hugging Face.

Open-source Llama-3.2-3B-Instruct model from meta-llama — available for download and self-hosting on Hugging Face.

Open-source tiny-Qwen2ForCausalLM-2.5 model from trl-internal-testing — available for download and self-hosting on Hugging Face.

Open-source Qwen3-1.7B model from qwen — available for download and self-hosting on Hugging Face.

Open-source Llama-3.1-8B-Instruct model from meta-llama — available for download and self-hosting on Hugging Face.

Open-source DeepSeek-V3.2 model from deepseek-ai — available for download and self-hosting on Hugging Face.

Open-source Qwen2.5-3B-Instruct model from qwen — available for download and self-hosting on Hugging Face.

Open-source Qwen2.5-1.5B-Instruct model from qwen — available for download and self-hosting on Hugging Face.

Open-source Qwen2.5-7B-Instruct model from qwen — available for download and self-hosting on Hugging Face.

Open-source Qwen3-0.6B model from qwen — available for download and self-hosting on Hugging Face.

autogluon/chronos-t5-tiny is a time series forecasting model on Hugging Face with ~74,825 monthly downloads. Open access.

facebook/nllb-200-3.3B is a translation model on Hugging Face with ~77,317 monthly downloads. Open access.

human-centered-summarization/financial-summarization-pegasus is a summarization model on Hugging Face with ~77,670 monthly downloads. Open access.

Vamsi/T5_Paraphrase_Paws is a text generation model on Hugging Face with ~97,285 monthly downloads. Open access.

Helsinki-NLP/opus-mt-en-zh is a translation model on Hugging Face with ~101,783 monthly downloads. Open access.

moussaKam/mbarthez is a fill mask model on Hugging Face with ~106,446 monthly downloads. Open access.

Helsinki-NLP/opus-mt-it-en is a translation model on Hugging Face with ~106,687 monthly downloads. Open access.

Helsinki-NLP/opus-mt-ar-en is a translation model on Hugging Face with ~120,850 monthly downloads. Open access.

XLabs-AI/xflux_text_encoders is a text generation model on Hugging Face with ~120,977 monthly downloads. Open access.

Helsinki-NLP/opus-mt-vi-en is a translation model on Hugging Face with ~122,834 monthly downloads. Open access.