Kendi bilgisayarınızda veya sunucunuzda ücretsiz çalıştırabileceğiniz modeller. Katalog ollama.com kütüphanesiyle canlı senkrondur · Son senkron: 13.08.2026 22:48.
233 model
Llama 3.1 is a new state-of-the-art model from Meta available in 8B, 70B and 405B parameter sizes.
⬇ 118.4M indirme · 93 varyant · 12.2024
DeepSeek-R1 is a family of open reasoning models with performance approaching that of leading models, such as O3 and Gemini 2.5 Pro.
⬇ 91.3M indirme · 35 varyant · 07.2025
A high-performing open embedding model with a large token context window.
⬇ 82.2M indirme · 3 varyant · 02.2024
Meta's Llama 3.2 goes small with 1B and 3B models.
⬇ 80M indirme · 63 varyant · 09.2024
The current, most capable model that runs on a single GPU.
⬇ 39.5M indirme · 26 varyant · 08.2025
Qwen2.5 models are pretrained on Alibaba's latest large-scale dataset, encompassing up to 18 trillion tokens. The model supports up to 128K tokens and has multilingual support.
⬇ 36.8M indirme · 133 varyant · 09.2024
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.
⬇ 34.1M indirme · 58 varyant · 10.2025
The 7B model released by Mistral AI, updated to version 0.3.
⬇ 31.9M indirme · 84 varyant · 07.2025
Google Gemma 2 is a high-performing and efficient model available in three sizes: 2B, 9B, and 27B.
⬇ 30.1M indirme · 94 varyant · 08.2024
Meta Llama 3: The most capable openly available LLM to date
⬇ 25M indirme · 68 varyant · 05.2024
Gemma 4 models are designed to deliver frontier-level performance at each size. They are well-suited for reasoning, agentic workflows, coding, and multimodal understanding.
⬇ 22M indirme · 49 varyant · 07.2026
The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing.
⬇ 20.3M indirme · 199 varyant · 05.2025
Phi-3 is a family of lightweight 3B (Mini) and 14B (Medium) state-of-the-art open models by Microsoft.
⬇ 18M indirme · 72 varyant · 07.2024
Qwen 3.5 is a family of open-source multimodal models that delivers exceptional utility and performance.
⬇ 17.4M indirme · 64 varyant · 05.2026
🌋 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.
⬇ 14.6M indirme · 98 varyant · 02.2024
State-of-the-art large embedding model from mixedbread.ai
⬇ 13.5M indirme · 4 varyant · 05.2024
OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.
⬇ 11.7M indirme · 5 varyant · 10.2025
Alibaba's performant long context models for agentic and coding tasks.
⬇ 8.2M indirme · 9 varyant · 09.2025
Phi-4 is a 14B parameter, state-of-the-art open model from Microsoft.
⬇ 7.7M indirme · 5 varyant · 01.2025
Qwen 1.5 is a series of large language models by Alibaba Cloud spanning from 0.5B to 110B parameters
⬇ 7.5M indirme · 379 varyant · 04.2024
Gemma is a family of lightweight, state-of-the-art open models built by Google DeepMind. Updated to version 1.1
⬇ 7.3M indirme · 102 varyant · 04.2024
Llama 2 is a collection of foundation language models ranging from 7B to 70B parameters.
⬇ 7.3M indirme · 102 varyant · 12.2023
GLM-OCR is a multimodal OCR model for complex document understanding, built on the GLM-V encoder–decoder architecture.
⬇ 7M indirme · 3 varyant · 02.2026
Qwen2 is a new series of large language models from Alibaba group
⬇ 6.1M indirme · 97 varyant · 09.2024
Bu modeller Ollama ile tek komutla bilgisayarınızda çalışır (Windows, macOS, Linux). Verileriniz cihazınızdan çıkmaz — gizlilik gerektiren işler için idealdir.
ollama run … komutunu terminale yapıştırın