AI Model Catalogue

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 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 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.

Elephant Alpha is a 100B-parameter text model focused on intelligence efficiency, delivering strong performance while minimizing token usage. It supports a 256K context window with up to 32K output tokens,...

Open-source bart-large-emojilm model from komeijiforce — available for download and self-hosting on Hugging Face.

Open-source t5gemma-s-s-prefixlm model from google — available for download and self-hosting on Hugging Face.

Open-source DeepSeek-R1-Distill-Qwen-32B model from deepseek-ai — available for download and self-hosting on Hugging Face.

Open-source h2ovl-mississippi-2b model from h2oai — available for download and self-hosting on Hugging Face.

Open-source h2ovl-mississippi-800m model from h2oai — available for download and self-hosting on Hugging Face.

Open-source NVIDIA-Nemotron-3-Super-120B-A12B-FP8 model from nvidia — available for download and self-hosting on Hugging Face.

Open-source SmolLM3-3B model from huggingfacetb — available for download and self-hosting on Hugging Face.

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

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

Open-source bloomz-560m model from bigscience — available for download and self-hosting on Hugging Face.

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

Open-source phi-2 model from microsoft — available for download and self-hosting on Hugging Face.