Self-Hosted AI with Ollama

InternLM2.5 is a 7B parameter model tailored for practical scenarios with outstanding reasoning capability.

Google Gemma 2 is a high-performing and efficient model available in three sizes: 2B, 9B, and 27B.

Phi-3 is a family of lightweight 3B (Mini) and 14B (Medium) state-of-the-art open models by Microsoft.

A series of models from Groq that represent a significant advancement in open-source AI capabilities for tool use/function calling.

A 3.8B model fine-tuned on a private high-quality synthetic dataset for information extraction, based on Phi-3.

CodeGemma is a collection of powerful, lightweight models that can perform a variety of coding tasks like fill-in-the-middle code completion, code generation, natural language understanding, mathematical reasoning, and instruction following.

A large language model that can use text prompts to generate and discuss code.

An open weights function calling model based on Llama 3, competitive with GPT-4o function calling capabilities.

MathΣtral: a 7B model designed for math reasoning and scientific discovery by Mistral AI.

A versatile model for AI software development scenarios, including code completion.

A strong multi-lingual general language model with competitive performance to Llama 3.

CodeQwen1.5 is a large language model pretrained on a large amount of code data.

A strong, economical, and efficient Mixture-of-Experts language model.

Aya 23, released by Cohere, is a new family of state-of-the-art, multilingual models that support 23 languages.

Meta Llama 3: The most capable openly available LLM to date

Falcon2 is an 11B parameters causal decoder-only model built by TII and trained over 5T tokens.

Yi 1.5 is a high-performing, bilingual language model.

A model from NVIDIA based on Llama 3 that excels at conversational question answering (QA) and retrieval-augmented generation (RAG).

Dolphin 2.9 is a new model with 8B and 70B sizes by Eric Hartford based on Llama 3 that has a variety of instruction, conversational, and coding skills.

A new small LLaVA model fine-tuned from Phi 3 Mini.

moondream2 is a small vision language model designed to run efficiently on edge devices.

A LLaVA model fine-tuned from Llama 3 Instruct with better scores in several benchmarks.

Stable LM 2 is a state-of-the-art 1.6B and 12B parameter language model trained on multilingual data in English, Spanish, German, Italian, French, Portuguese, and Dutch.

This model extends LLama-3 8B's context length from 8k to over 1m tokens.

Qwen 1.5 is a series of large language models by Alibaba Cloud spanning from 0.5B to 110B parameters

DBRX is an open, general-purpose LLM created by Databricks.

State of the art large language model from Microsoft AI with improved performance on complex chat, multilingual, reasoning and agent use cases.

Zephyr is a series of fine-tuned versions of the Mistral and Mixtral models that are trained to act as helpful assistants.

Gemma is a family of lightweight, state-of-the-art open models built by Google DeepMind. Updated to version 1.1

A 7B and 15B uncensored variant of the Dolphin model family that excels at coding, based on StarCoder2.