phi4-mini-reasoning
Phi 4 mini reasoning is a lightweight open model that balances efficiency with advanced reasoning ability.
3.8b
⬇ 288.2K indirme · 5 varyant · 05.2025
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
granite3.3
IBM Granite 2B and 8B models are 128K context length language models that have been fine-tuned for improved reasoning and instruction-following capabilities.
Araç Kullanımı
2b
8b
⬇ 1.1M indirme · 3 varyant · 04.2025
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
cogito
Cogito v1 Preview is a family of hybrid reasoning models by Deep Cogito that outperform the best available open models of the same size, including counterparts from LLaMA, DeepSeek, and Qwen across most standard benchmarks.
Araç Kullanımı
3b
8b
14b
32b
⬇ 2.1M indirme · 20 varyant · 04.2025
mistral-small3.1
Building upon Mistral Small 3, 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.
Görüntü
Araç Kullanımı
24b
⬇ 777.2K indirme · 5 varyant · 04.2025
openthinker
A fully open-source family of reasoning models built using a dataset derived by distilling DeepSeek-R1.
7b
32b
⬇ 1.2M indirme · 15 varyant · 04.2025
exaone-deep
EXAONE Deep exhibits superior capabilities in various reasoning tasks including math and coding benchmarks, ranging from 2.4B to 32B parameters developed and released by LG AI Research.
2.4b
7.8b
32b
⬇ 758K indirme · 13 varyant · 03.2025
qwq
QwQ is the reasoning model of the Qwen series.
Araç Kullanımı
32b
⬇ 2.3M indirme · 8 varyant · 03.2025
command-a
111 billion parameter model optimized for demanding enterprises that require fast, secure, and high-quality AI
Araç Kullanımı
111b
⬇ 224K indirme · 5 varyant · 03.2025
command-r7b-arabic
A new state-of-the-art version of the lightweight Command R7B model that excels in advanced Arabic language capabilities for enterprises in the Middle East and Northern Africa.
Araç Kullanımı
7b
⬇ 200.4K indirme · 5 varyant · 03.2025
phi4-mini
Phi-4-mini brings significant enhancements in multilingual support, reasoning, and mathematics, and now, the long-awaited function calling feature is finally supported.
Araç Kullanımı
3.8b
⬇ 1.4M indirme · 5 varyant · 02.2025
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
granite3.2
Granite-3.2 is a family of long-context AI models from IBM Granite fine-tuned for thinking capabilities.
Araç Kullanımı
2b
8b
⬇ 449.8K indirme · 9 varyant · 02.2025
r1-1776
A version of the DeepSeek-R1 model that has been post trained to provide unbiased, accurate, and factual information by Perplexity.
70b
671b
⬇ 415.7K indirme · 9 varyant · 02.2025
deepscaler
A fine-tuned version of Deepseek-R1-Distilled-Qwen-1.5B that surpasses the performance of OpenAI’s o1-preview with just 1.5B parameters on popular math evaluations.
1.5b
⬇ 1.3M indirme · 5 varyant · 02.2025
mistral-small
Mistral Small 3 sets a new benchmark in the “small” Large Language Models category below 70B.
Araç Kullanımı
22b
24b
⬇ 3.1M indirme · 21 varyant · 01.2025
granite3.1-dense
The IBM Granite 2B and 8B models are text-only dense LLMs trained on over 12 trillion tokens of data, demonstrated significant improvements over their predecessors in performance and speed in IBM’s initial testing.
Araç Kullanımı
2b
8b
⬇ 1M indirme · 33 varyant · 01.2025
granite3.1-moe
The IBM Granite 1B and 3B models are long-context mixture of experts (MoE) Granite models from IBM designed for low latency usage.
Araç Kullanımı
1b
3b
⬇ 3M indirme · 33 varyant · 01.2025
command-r7b
The smallest model in Cohere's R series delivers top-tier speed, efficiency, and quality to build powerful AI applications on commodity GPUs and edge devices.
Araç Kullanımı
7b
⬇ 292.9K indirme · 5 varyant · 01.2025
deepseek-v3
A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.
671b
⬇ 3.8M indirme · 5 varyant · 01.2025
olmo2
OLMo 2 is a new family of 7B and 13B models trained on up to 5T tokens. These models are on par with or better than equivalently sized fully open models, and competitive with open-weight models such as Llama 3.1 on English academic benchmarks.
7b
13b
⬇ 3.7M indirme · 9 varyant · 01.2025
phi4
Phi-4 is a 14B parameter, state-of-the-art open model from Microsoft.
14b
⬇ 7.7M indirme · 5 varyant · 01.2025
dolphin3
Dolphin 3.0 Llama 3.1 8B 🐬 is the next generation of the Dolphin series of instruct-tuned models designed to be the ultimate general purpose local model, enabling coding, math, agentic, function calling, and general use cases.
8b
⬇ 4M indirme · 5 varyant · 01.2025
smallthinker
A new small reasoning model fine-tuned from the Qwen 2.5 3B Instruct model.
3b
⬇ 255K indirme · 5 varyant · 12.2024
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