AI Model Catalogue

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

Open-source TinyWord-134k model from harley-ml — available for download and self-hosting on Hugging Face.

Open-source acquisition_student_filtered_qwen3bins_numina model from ishikaa — available for download and self-hosting on Hugging Face.

Open-source acquisition_student_filtered_qwen3bins_medmcqa model from ishikaa — available for download and self-hosting on Hugging Face.

Open-source mind-mem-4b model from star-ga — available for download and self-hosting on Hugging Face.

Qwen1.5 is the improved version of Qwen, the large language model series developed by Alibaba Cloud.

Building upon Mistral Small 3 (2501), Mistral Small 3.1 (2503) adds state-of-the-art vision understanding and enhances long context capabilities up to 128k tokens without compromising text performance. With 24 billion parameters, this model achieves top-tier capabilities in both text and vision tasks.

The Llama 3.2-Vision instruction-tuned models are optimized for visual recognition, image reasoning, captioning, and answering general questions about an image.

BAAI general embedding (Base) model that transforms any given text into a 768-dimensional vector

SEA-LION stands for Southeast Asian Languages In One Network, which is a collection of Large Language Models (LLMs) which have been pretrained and instruct-tuned for the Southeast Asia (SEA) region.

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support.

Quantized (int4) generative text model with 8 billion parameters from Meta.

UForm-Gen is a small generative vision-language model primarily designed for Image Captioning and Visual Question Answering. The model was pre-trained on the internal image captioning dataset and fine-tuned on public instructions datasets: SVIT, LVIS, VQAs datasets.

This is a Gemma-7B base model that Cloudflare dedicates for inference with LoRA adapters. Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models.

Gemma 4 is Google's most intelligent family of open models, built from Gemini 3 research to maximize intelligence-per-parameter.

This model is intended to be used by non-technical users to understand data inside their SQL databases.

Phi-2 is a Transformer-based model with a next-word prediction objective, trained on 1.4T tokens from multiple passes on a mixture of Synthetic and Web datasets for NLP and coding.

BART is a transformer encoder-encoder (seq2seq) model with a bidirectional (BERT-like) encoder and an autoregressive (GPT-like) decoder. You can use this model for text summarization.

OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases – gpt-oss-20b is for lower latency, and local or specialized use-cases.

EmbeddingGemma is a 300M parameter, state-of-the-art for its size, open embedding model from Google, built from Gemma 3 (with T5Gemma initialization) and the same research and technology used to create Gemini models. EmbeddingGemma produces vector representations of text, making it well-suited for search and retrieval tasks, including classification, clustering, and semantic similarity search. This model was trained with data in 100+ spoken languages.

Different from embedding model, reranker uses question and document as input and directly output similarity instead of embedding. You can get a relevance score by inputting query and passage to the reranker. And the score can be mapped to a float value in [0,1] by sigmoid function.

Qwen1.5 is the improved version of Qwen, the large language model series developed by Alibaba Cloud. AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization.

OpenChat is an innovative library of open-source language models, fine-tuned with C-RLFT - a strategy inspired by offline reinforcement learning.

Meta's Llama 4 Scout is a 17 billion parameter model with 16 experts that is natively multimodal. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding.

QwQ is the reasoning model of the Qwen series. Compared with conventional instruction-tuned models, QwQ, which is capable of thinking and reasoning, can achieve significantly enhanced performance in downstream tasks, especially hard problems. QwQ-32B is the medium-sized reasoning model, which is capable of achieving competitive performance against state-of-the-art reasoning models, e.g., DeepSeek-R1, o1-mini.

Quantized (int4) generative text model with 8 billion parameters from Meta.

Gemma 3 models are well-suited for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Gemma 3 models are multimodal, handling text and image input and generating text output, with a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions.

BAAI general embedding (Large) model that transforms any given text into a 1024-dimensional vector

The TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens. This is the chat model finetuned on top of TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T.

Qwen1.5 is the improved version of Qwen, the large language model series developed by Alibaba Cloud. AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization.

Qwen1.5 is the improved version of Qwen, the large language model series developed by Alibaba Cloud.

Multi-Functionality, Multi-Linguality, and Multi-Granularity embeddings model.

Distilled BERT model that was finetuned on SST-2 for sentiment classification