AI Model Catalogue

Open-source distilgpt2 model from distilbert — available for download and self-hosting on Hugging Face.

Open-source gpt2-large model from openai-community — available for download and self-hosting on Hugging Face.

vikhyatk/moondream2 is a image text to text model on Hugging Face with ~2,723,483 monthly downloads. Open access.

Open-source Qwen3-14B model from qwen — available for download and self-hosting on Hugging Face.

deepseek-ai/DeepSeek-V3.2 is a text generation model on Hugging Face with ~2,756,798 monthly downloads. Open access.

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

Qwen/Qwen2-1.5B-Instruct is a text generation model on Hugging Face with ~2,929,131 monthly downloads. Open access.

TinyLlama/TinyLlama-1.1B-Chat-v1.0 is a text generation model on Hugging Face with ~3,019,986 monthly downloads. Open access.

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

Open-source gpt-oss-120b model from openai — available for download and self-hosting on Hugging Face.

Open-source DeepSeek-R1 model from deepseek-ai — available for download and self-hosting on Hugging Face.

Qwen/Qwen2.5-32B-Instruct is a text generation model on Hugging Face with ~4,108,805 monthly downloads. Open access.

meta-llama/Llama-3.2-1B-Instruct is a text generation model on Hugging Face with ~4,183,435 monthly downloads. (Gated access — requires HuggingFace login.)

dphn/dolphin-2.9.1-yi-1.5-34b is a text generation model on Hugging Face with ~4,425,207 monthly downloads. Open access.

meta-llama/Llama-3.2-3B-Instruct is a text generation model on Hugging Face with ~5,336,740 monthly downloads. (Gated access — requires HuggingFace login.)

Qwen/Qwen2.5-0.5B-Instruct is a text generation model on Hugging Face with ~5,490,575 monthly downloads. Open access.

Open-source gpt-oss-20b model from openai — available for download and self-hosting on Hugging Face.

Qwen/Qwen3-Embedding-0.6B is a feature extraction model on Hugging Face with ~6,081,757 monthly downloads. Open access.

trl-internal-testing/tiny-Qwen2ForCausalLM-2.5 is a text generation model on Hugging Face with ~6,423,307 monthly downloads. Open access.

Open-source opt-125m model from facebook — available for download and self-hosting on Hugging Face.

Open-source Qwen3-4B-Instruct-2507 model from qwen — available for download and self-hosting on Hugging Face.

Qwen/Qwen3-1.7B is a text generation model on Hugging Face with ~8,067,534 monthly downloads. Open access.

Open-source Qwen3-4B model from qwen — available for download and self-hosting on Hugging Face.

Open-source Qwen3-8B model from qwen — available for download and self-hosting on Hugging Face.

Qwen/Qwen2.5-3B-Instruct is a text generation model on Hugging Face with ~8,750,507 monthly downloads. Open access.

meta-llama/Llama-3.1-8B-Instruct is a text generation model on Hugging Face with ~9,266,275 monthly downloads. (Gated access — requires HuggingFace login.)

Qwen/Qwen2.5-1.5B-Instruct is a text generation model on Hugging Face with ~9,915,572 monthly downloads. Open access.

Qwen/Qwen2.5-7B-Instruct is a text generation model on Hugging Face with ~12,936,213 monthly downloads. Open access.

Open-source gpt2 model from openai-community — available for download and self-hosting on Hugging Face.

Qwen/Qwen3-0.6B is a text generation model on Hugging Face with ~15,133,638 monthly downloads. Open access.

Samsung Gauss 2 is Samsung's large language model optimized for on-device and cloud workloads. Trained on multilingual data with a focus on Korean and English, covering general conversation, summarization, and code assistance.

Qwen3 235B A22B is Alibaba's flagship mixture-of-experts model with 235B total parameters and 22B active per token. Delivers frontier-level performance on coding, reasoning, and multilingual tasks at significantly lower inference cost.

Falcon 180B is one of the largest openly available language models, trained on 3.5 trillion tokens with TII's custom RefinedWeb dataset. Excels at reasoning, summarization, and generation tasks at state-of-the-art quality for open models.