AI Model Catalogue

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.

DBRX Instruct is an open, general-purpose LLM from Databricks. Built with a fine-grained mixture-of-experts (MoE) architecture, it was the most capable open LLM at launch and excels at code, math, and language tasks.

NVIDIA Nemotron-4 340B Instruct is a large open language model trained to generate diverse synthetic data for training other LLMs. Strong at following instructions, classification, and generating reward model training data.

AI21 Jamba 1.6 Mini is a lightweight Mamba-Transformer hybrid optimized for cost-effective, high-throughput inference with an impressive 256K context window. An excellent choice for document-heavy workloads on a budget.

AI21 Jamba 1.6 Large uses a hybrid Mamba-Transformer architecture offering low memory footprint and high throughput compared to equivalent Transformer models. Features 256K context at a fraction of the inference cost.

Microsoft Phi-4 Mini is a 3.8B parameter compact model from Microsoft. Delivers impressive reasoning capabilities for edge and mobile deployment scenarios, with strong performance on math and coding tasks relative to its size.

IBM Granite 3.0 2B Instruct is an ultra-compact enterprise model excelling at summarization, extraction, and classification. The smallest model in the Granite family, suitable for edge deployments and constrained environments.

IBM Granite 3.0 8B Instruct is a lightweight enterprise-grade language model trained on a carefully curated enterprise corpus and optimized for RAG, summarization, classification, and code generation in business contexts.

Amazon Titan Text Express is a generative LLM for summarization, text generation, classification, open-ended Q&A, and information extraction. Optimized for enterprise workloads via AWS Bedrock.

Amazon Nova Pro is a highly capable multimodal model with the best combination of accuracy, speed, and cost across a wide range of tasks. Supports text, image, and video inputs.