samantha-mistral
A companion assistant trained in philosophy, psychology, and personal relationships. Based on Mistral.
7b
⬇ 985.9K indirme · 49 varyant · 10.2023
Açık Kaynak AI Modelleri
Kendi bilgisayarınızda veya sunucunuzda ücretsiz çalıştırabileceğiniz modeller. Katalog ollama.com kütüphanesiyle canlı senkrondur · Son senkron: 13.08.2026 22:48.
233 model
llama3-gradient
This model extends LLama-3 8B's context length from 8k to over 1m tokens.
8b
70b
⬇ 985.1K indirme · 35 varyant · 05.2024
llama3-groq-tool-use
A series of models from Groq that represent a significant advancement in open-source AI capabilities for tool use/function calling.
Araç Kullanımı
8b
70b
⬇ 979.3K indirme · 33 varyant · 07.2024
xwinlm
Conversational model based on Llama 2 that performs competitively on various benchmarks.
7b
13b
⬇ 972.9K indirme · 80 varyant · 11.2023
granite3.2-vision
A compact and efficient vision-language model, specifically designed for visual document understanding, enabling automated content extraction from tables, charts, infographics, plots, diagrams, and more.
Görüntü
Araç Kullanımı
2b
⬇ 971.6K indirme · 5 varyant · 02.2025
starling-lm
Starling is a large language model trained by reinforcement learning from AI feedback focused on improving chatbot helpfulness.
7b
⬇ 967.5K indirme · 36 varyant · 04.2024
phind-codellama
Code generation model based on Code Llama.
34b
⬇ 956.6K indirme · 49 varyant · 12.2023
yarn-llama2
An extension of Llama 2 that supports a context of up to 128k tokens.
7b
13b
⬇ 954.3K indirme · 67 varyant · 11.2023
solar
A compact, yet powerful 10.7B large language model designed for single-turn conversation.
10.7b
⬇ 950.8K indirme · 32 varyant · 12.2023
deepcoder
DeepCoder is a fully open-Source 14B coder model at O3-mini level, with a 1.5B version also available.
1.5b
14b
⬇ 940.4K indirme · 9 varyant · 04.2025
granite3-moe
The IBM Granite 1B and 3B models are the first mixture of experts (MoE) Granite models from IBM designed for low latency usage.
Araç Kullanımı
1b
3b
⬇ 937.8K indirme · 33 varyant · 11.2024
devstral-small-2
24B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.
Görüntü
Araç Kullanımı
24b
⬇ 935.1K indirme · 6 varyant · 12.2025
paraphrase-multilingual
Sentence-transformers model that can be used for tasks like clustering or semantic search.
Embedding
278m
⬇ 934.2K indirme · 3 varyant · 08.2024
stable-beluga
Llama 2 based model fine tuned on an Orca-style dataset. Originally called Free Willy.
7b
13b
70b
⬇ 922.3K indirme · 49 varyant · 10.2023
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
⬇ 920.6K indirme · 33 varyant · 11.2023
shieldgemma
ShieldGemma is set of instruction tuned models for evaluating the safety of text prompt input and text output responses against a set of defined safety policies.
2b
9b
27b
⬇ 913.3K indirme · 49 varyant · 10.2024
reader-lm
A series of models that convert HTML content to Markdown content, which is useful for content conversion tasks.
0.5b
1.5b
⬇ 912.6K indirme · 33 varyant · 09.2024
llama-pro
An expansion of Llama 2 that specializes in integrating both general language understanding and domain-specific knowledge, particularly in programming and mathematics.
⬇ 896.6K indirme · 33 varyant · 01.2024
yarn-mistral
An extension of Mistral to support context windows of 64K or 128K.
7b
⬇ 887.3K indirme · 33 varyant · 11.2023
wizardlm
General use model based on Llama 2.
⬇ 885.3K indirme · 73 varyant · 10.2023
nexusraven
Nexus Raven is a 13B instruction tuned model for function calling tasks.
13b
⬇ 882.5K indirme · 32 varyant · 01.2024
bakllava
BakLLaVA is a multimodal model consisting of the Mistral 7B base model augmented with the LLaVA architecture.
Görüntü
7b
⬇ 875.8K indirme · 17 varyant · 12.2023
meditron
Open-source medical large language model adapted from Llama 2 to the medical domain.
7b
70b
⬇ 815.3K indirme · 22 varyant · 12.2023
command-r-plus
Command R+ is a powerful, scalable large language model purpose-built to excel at real-world enterprise use cases.
Araç Kullanımı
104b
⬇ 788.4K indirme · 21 varyant · 08.2024
Açık kaynak model nasıl çalıştırılır?
Bu modeller Ollama ile tek komutla bilgisayarınızda çalışır (Windows, macOS, Linux). Verileriniz cihazınızdan çıkmaz — gizlilik gerektiren işler için idealdir.
- ollama.com/download adresinden Ollama'yı kurun
- Model sayfasındaki
ollama run …komutunu terminale yapıştırın - İlk indirme sonrası model tamamen çevrimdışı çalışır