AI Model Catalogue

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

This is a Gemma-2B 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.

Generation over generation, Meta Llama 3 demonstrates state-of-the-art performance on a wide range of industry benchmarks and offers new capabilities, including improved reasoning.

The Llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks.

Kimi K2.5 is a frontier-scale open-source model with a 256k context window, multi-turn tool calling, vision inputs, and structured outputs for agentic workloads.

Llama Guard 3 is a Llama-3.1-8B pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification) and in LLM responses (response classification). It acts as an LLM – it generates text in its output that indicates whether a given prompt or response is safe or unsafe, and if unsafe, it also lists the content categories violated.

The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks.

Full precision (fp16) generative text model with 7 billion parameters from Meta

Instruct fine-tuned version of the Mistral-7b generative text model with 7 billion parameters

The Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-7B-v0.2.

Cybertron 7B v2 is a 7B MistralAI based model, best on it's series. It was trained with SFT, DPO and UNA (Unified Neural Alignment) on multiple datasets.

LLaVA is an open-source chatbot trained by fine-tuning LLaMA/Vicuna on GPT-generated multimodal instruction-following data. It is an auto-regressive language model, based on the transformer architecture.

DiscoLM German 7b is a Mistral-based large language model with a focus on German-language applications. AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization.

Quantized (int8) generative text model with 7 billion parameters from Meta

Llama 3.1 8B quantized to FP8 precision

GLM-4.7-Flash is a fast and efficient multilingual text generation model with a 131,072 token context window. Optimized for dialogue, instruction-following, and multi-turn tool calling across 100+ languages.

50 layers deep image classification CNN trained on more than 1M images from ImageNet

This is a Llama2 base model that Cloudflare dedicated for inference with LoRA adapters. Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the repository for the 7B fine-tuned model, optimized for dialogue use cases and converted for the Hugging Face Transformers format.

Llama 3.3 70B quantized to fp8 precision, optimized to be faster.

Granite 4.0 instruct models deliver strong performance across benchmarks, achieving industry-leading results in key agentic tasks like instruction following and function calling. These efficiencies make the models well-suited for a wide range of use cases like retrieval-augmented generation (RAG), multi-agent workflows, and edge deployments.

Multilingual encoder-decoder (seq-to-seq) model trained for Many-to-Many multilingual translation

IndicTrans2 is the first open-source transformer-based multilingual NMT model that supports high-quality translations across all the 22 scheduled Indic languages

BAAI general embedding (Small) model that transforms any given text into a 384-dimensional vector

Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). As of now, Qwen2.5-Coder has covered six mainstream model sizes, 0.5, 1.5, 3, 7, 14, 32 billion parameters, to meet the needs of different developers. Qwen2.5-Coder brings the following improvements upon CodeQwen1.5:

DeepSeekMath-Instruct 7B is a mathematically instructed tuning model derived from DeepSeekMath-Base 7B. DeepSeekMath is initialized with DeepSeek-Coder-v1.5 7B and continues pre-training on math-related tokens sourced from Common Crawl, together with natural language and code data for 500B tokens.

Falcon-7B-Instruct is a 7B parameters causal decoder-only model built by TII based on Falcon-7B and finetuned on a mixture of chat/instruct datasets.

NVIDIA Nemotron 3 Super is a hybrid MoE model with leading accuracy for multi-agent applications and specialized agentic AI systems.

Kimi K2.6 is a frontier-scale open-source 1T parameter model with a 262.1k context window, multi-turn tool calling, vision inputs, and structured outputs for agentic workloads.