https://DevOpsCloud.io -- Cloud Monk Losang Jinpa, Ph.D., MCSE/MCT, GitOps DevOps Engineer

llama3.1

Llama 3.1 is a new state-of-the-art model from Meta available in 8B, 70B and 405B parameter sizes.

Tools 8B 70B

2.2M

Pulls

95

Tags

Updated 4 weeks ago

gemma2 Google Gemma 2 is a high-performing and efficient model by now available in three sizes: 2B, 9B, and 27B.

2B 9B 27B 944.4K

Pulls

Tags

mistral-nemo A state-of-the-art 12B model with 128k context length, built by Mistral AI in collaboration with NVIDIA.

Tools 12B 110.9K

Pulls

Tags

mistral-large Mistral Large 2 is Mistral's new flagship model that is significantly more capable in code generation, mathematics, and reasoning with 128k context window and support for dozens of languages.

Tools 123B 44.6K

Pulls

Tags

qwen2 Qwen2 is a new series of large language models from Alibaba group

0.5B 1.5B 7B 72B 2.2M

Pulls

Tags

deepseek-coder-v2 An open-source Mixture-of-Experts code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks.

Code 16B 236B 231.9K

Pulls

Tags

phi3 Phi-3 is a family of lightweight 3B (Mini) and 14B (Medium) state-of-the-art open models by Microsoft.

3B 14B 2.3M

Pulls

Tags

mistral

The 7B model released by Mistral AI, updated to version 0.3.

Tools 7B 3.3M

Pulls

Tags

mixtral

A set of Mixture of Experts (MoE) model with open weights by Mistral AI in 8x7b and 8x22b parameter sizes.

Tools 8x7B 8x22B 384.2K

Pulls

Tags

codegemma

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.

Code 2B 7B 244.1K

Pulls

Tags

Command R is a Large Language Model optimized for conversational interaction and long context tasks.

35B 162K

Pulls

Tags

Command R Plus | Command R+ is a powerful, scalable large language model purpose-built to excel at real-world enterprise use cases.

Tools 104B 90K

Pulls

Tags

🌋 LLaVA is a novel end-to-end trained large multimodal model that combines a vision encoder and Vicuna for general-purpose visual and language understanding. Updated to version 1.6.

Vision 7B 13B 34B 806K

Pulls

Tags

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

8B 70B 5.8M

Pulls

Tags

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

2B 7B 4.1M

Pulls

Tags

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

0.5B 1.8B 4B 32B 72B 110B 3.9M

Pulls

Tags

Llama 2 is a collection of foundation language models ranging from 7B to 70B parameters.

7B 13B 70B 2M

Pulls

Tags

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

Code 7B 13B 34B 70B 986.8K

Pulls

Tags

Uncensored, 8x7b and 8x22b fine-tuned models based on the Mixtral mixture of experts models that excels at coding tasks. Created by Eric Hartford.

8x7B 8x22B 363.9K

Pulls

Tags

A high-performing open embedding model with a large token context window.

Embedding 355K

Pulls

Tags

Uncensored Llama 2 model by George Sung and Jarrad Hope.

7B 284K

Pulls

Tags

Phi-2: a 2.7B language model by Microsoft Research that demonstrates outstanding reasoning and language understanding capabilities.

3B 276.2K

Pulls

Tags

DeepSeek Coder is a capable coding model trained on two trillion code and natural language tokens.

Code 1B 7B 33B 262.4K

Pulls

Tags

State-of-the-art large embedding model from mixedbread.ai

Embedding 215.8K

Pulls

Tags

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

7B 8x22B 201.9K

Pulls

Tags

The uncensored Dolphin model based on Mistral that excels at coding tasks. Updated to version 2.8.

7B 193.5K

Pulls

Tags

A general-purpose model ranging from 3 billion parameters to 70 billion, suitable for entry-level hardware.

3B 7B 13B 178.6K

Pulls

Tags

StarCoder2 is the next generation of transparently trained open code LLMs that comes in three sizes: 3B, 7B and 15B parameters.

Code 3B 7B 178.4K

Pulls

Tags

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.

8B 70B 176K

Pulls

Tags

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

6B 9B 34B 152.9K

Pulls

Tags

Mistral OpenOrca is a 7 billion parameter model, fine-tuned on top of the Mistral 7B model using the OpenOrca dataset.

7B 140.2K

Pulls

Tags

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

Vision 8B 126.7K

Pulls

Tags

StarCoder is a code generation model trained on 80+ programming languages.

Code 1B 3B 7B 15B 121.3K

Pulls

Tags

Llama 2 based model fine tuned to improve Chinese dialogue ability.

7B 13B 120K

Pulls

Tags

General use chat model based on Llama and Llama 2 with 2K to 16K context sizes.

7B 13B 30B 114.4K

Pulls

Tags

The TinyLlama project is an open endeavor to train a compact 1.1B Llama model on 3 trillion tokens.

1B 111.3K

Pulls

Tags

Codestral is Mistral AI’s first-ever code model designed for code generation tasks.

Code 22B 106.9K

Pulls

Tags

wizard-vicuna-uncensored

Wizard Vicuna Uncensored is a 7B, 13B, and 30B parameter model based on Llama 2 uncensored by Eric Hartford.

7B 13B 30B 103.6K

Pulls

Tags

nous-hermes2

The powerful family of models by Nous Research that excels at scientific discussion and coding tasks.

34B 101.1K

Pulls

Tags

openchat

A family of open-source models trained on a wide variety of data, surpassing ChatGPT on various benchmarks. Updated to version 3.5-0106.

7B 88K

Pulls

Tags

wizardlm2

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

7B 8x22B 87.8K

Pulls

Tags

aya

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

8B 35B 87.3K

Pulls

Tags

tinydolphin

An experimental 1.1B parameter model trained on the new Dolphin 2.8 dataset by Eric Hartford and based on TinyLlama.

1B 83.8K

Pulls

Tags

wizardcoder

State-of-the-art code generation model

Code 7B 13B 33B 34B 79.5K

Pulls

Tags

Stable Code 3B is a coding model with instruct and code completion variants on par with models such as Code Llama 7B that are 2.5x larger.

Code 79.3K

Pulls

Tags

OpenHermes 2.5 is a 7B model fine-tuned by Teknium on Mistral with fully open datasets.

7B 76.9K

Pulls

Tags

granite-code

A family of open foundation models by IBM for Code Intelligence

Code 3B 8B 75.4K

Pulls

Tags

all-minilm

Embedding models on very large sentence level datasets.

Embedding 22M 33M 72.6K

Pulls

Tags

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

Code 7B 69.1K

Pulls

Tags

stablelm2

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.

1.6B 12B 66.1K

Pulls

Tags

wizard-math

Model focused on math and logic problems

7B 13B 65.7K

Pulls

Tags

neural-chat

A fine-tuned model based on Mistral with good coverage of domain and language.

7B 62.6K

Pulls

Tags

llama3-gradient

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

8B 70B 60K

Pulls

Tags

phind-codellama] [[Code generation model based on Code Llama.

Code 34B 56.6K

Pulls

Tags

dolphincoder

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

Code 7B 54.1K

Pulls

Tags

nous-hermes

General use models based on Llama and Llama 2 from Nous Research.

7B 13B 54.1K

Pulls

Tags

SQLCoder is a code completion model fined-tuned on StarCoder for SQL generation tasks

Code 7B 15B 70B 53.6K

Pulls

Tags

xwinlm

Conversational model based on Llama 2 that performs competitively on various benchmarks.

7B 13B 51.9K

Pulls

Tags

deepseek-llm

An advanced language model crafted with 2 trillion bilingual tokens.

7B 67B 50.6K

Pulls

Tags

yarn-llama2

An extension of Llama 2 that supports a context of up to 128k tokens.

7B 13B 50.5K

Pulls

Tags

llama3-chatqa

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

8B 70B 48.8K

Pulls

Tags

starling-lm

Starling is a large language model trained by reinforcement learning from AI feedback focused on improving chatbot helpfulness.

7B 48.2K

Pulls

Tags

wizardlm

General use model based on Llama 2.

7B 13B 30B 47.4K

Pulls

Tags

falcon

Archive

A large language model built by the Technology Innovation Institute (TII) for use in summarization, text generation, and chat bots.

7B 40B 180B 45.9K

Pulls

Tags

orca2

Orca 2 is built by Microsoft Research, and are a fine-tuned version of Meta's Llama 2 models. The model is designed to excel particularly in reasoning.

7B 13B 44.5K

Pulls

Tags

snowflake-arctic-embed

A suite of text embedding models by Snowflake, optimized for performance.

Embedding 22M 33M 44.4K

Pulls

Tags

solar

A compact, yet powerful 10.7B large language model designed for single-turn conversation.

43.6K

Pulls

Tags

samantha-mistral

A companion assistant trained in philosophy, psychology, and personal relationships. Based on Mistral.

7B 43K

Pulls

Tags

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

Vision 41K

Pulls

Tags

stable-beluga

Llama 2 based model fine tuned on an Orca-style dataset. Originally called Free Willy.

7B 13B 38.1K

Pulls

Tags

dolphin-phi

2.7B uncensored Dolphin model by Eric Hartford, based on the Phi language model by Microsoft Research.

3B 37.5K

Pulls

Tags

deepseek-v2

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

16B 236B 35.4K

Pulls

Tags

bakllava

BakLLaVA is a multimodal model consisting of the Mistral 7B base model augmented with the LLaVA architecture.

Vision 7B 34.7K

Pulls

Tags

wizardlm-uncensored

Uncensored version of Wizard LM model

13B 32.8K

Pulls

Tags

glm4

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

9B 31.5K

Pulls

Tags

yarn-mistral

An extension of Mistral to support context windows of 64K or 128K.

7B 30.5K

Pulls

Tags

medllama2

Fine-tuned Llama 2 model to answer medical questions based on an open source medical dataset.

7B 30.3K

Pulls

Tags

llama-pro

An expansion of Llama 2 that specializes in integrating both general language understanding and domain-specific knowledge, particularly in programming and mathematics.

8B 29.5K

Pulls

Tags

codegeex4

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

Code 9B 28.7K

Pulls

Tags

nous-hermes2-mixtral

The Nous Hermes 2 model from Nous Research, now trained over Mixtral.

8x7B 27.6K

Pulls

Tags

meditron

Open-source medical large language model adapted from Llama 2 to the medical domain.

7B 70B 27.6K

Pulls

Tags

llava-phi3

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

Vision 3B 27.2K

Pulls

Tags

nexusraven

Nexus Raven is a 13B instruction tuned model for function calling tasks.

13B 26.8K

Pulls

Tags

codeup

Great code generation model based on Llama2.

Code 13B 25.6K

Pulls

Tags

everythinglm

Uncensored Llama2 based model with support for a 16K context window.

13B 24.1K

Pulls

Tags

magicoder

🎩 Magicoder is a family of 7B parameter models trained on 75K synthetic instruction data using OSS-Instruct, a novel approach to enlightening LLMs with open-source code snippets.

Code 7B 21.5K

Pulls

Tags

stablelm-zephyr

A lightweight chat model allowing accurate, and responsive output without requiring high-end hardware.

21.1K

Pulls

Tags

codebooga

A high-performing code instruct model created by merging two existing code models.

Code 34B 20.3K

Pulls

Tags

mistrallite

MistralLite is a fine-tuned model based on Mistral with enhanced capabilities of processing long contexts.

7B 19.4K

Pulls

Tags

internlm2

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

7B 18.6K

Pulls

Tags

wizard-vicuna

Wizard Vicuna is a 13B parameter model based on Llama 2 trained by MelodysDreamj.

13B 17.8K

Pulls

Tags

duckdb-nsql

7B parameter text-to-SQL model made by MotherDuck and Numbers Station.

Code 7B 17.4K

Pulls

Tags

phi3.5

A lightweight AI model with 3.8 billion parameters with performance overtaking similarly and larger sized models.

3B 17.3K

Pulls

Tags

falcon2]

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

11B 17K

Pulls

Tags

megadolphin

MegaDolphin-2.2-120b is a transformation of Dolphin-2.2-70b created by interleaving the model with itself.

16.3K

Pulls

Tags

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

Tools 8B 70B 16.1K

Pulls

Tags

notux

A top-performing mixture of experts model, fine-tuned with high-quality data.

8x7B 15.7K

Pulls

Tags

goliath

A language model created by combining two fine-tuned Llama 2 70B models into one.

15.6K

Pulls

Tags

open-orca-platypus2

Merge of the Open Orca OpenChat model and the Garage-bAInd Platypus 2 model. Designed for chat and code generation.

13B 15.5K

Pulls

Tags

notus

A 7B chat model fine-tuned with high-quality data and based on Zephyr.

7B 15K

Pulls

Tags

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

132B 13.2K

Pulls

Tags

mathstral

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

7B 9,927

Pulls

Tags

alfred

A robust conversational model designed to be used for both chat and instruct use cases.

9,841

Pulls

Tags

nuextract

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

3B 6,149

Pulls

Tags

firefunction-v2

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

Tools 70B 6,131

Pulls

Tags

smollm

🪐 A family of small models with 135M, 360M, and 1.7B parameters, trained on a new high-quality dataset.

5,475

Pulls

Tags

bge-m3

BGE-M3 is a new model from BAAI distinguished for its versatility in Multi-Functionality, Multi-Linguality, and Multi-Granularity.

Embedding 5,092

Pulls

Tags

bge-large

Embedding model from BAAI mapping texts to vectors.

Embedding 2,900

Pulls

Tags

paraphrase-multilingual

Sentence-transformers model that can be used for tasks like clustering or semantic search.

https://ollama.com/library