gemma2
Google Gemma 2 is a high-performing and efficient model available in three sizes: 2B, 9B, and 27B.
2b
9b
27b
⬇ 30.1M indirme · 94 varyant · 08.2024
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
phi3
Phi-3 is a family of lightweight 3B (Mini) and 14B (Medium) state-of-the-art open models by Microsoft.
3.8b
14b
⬇ 18M indirme · 72 varyant · 07.2024
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
nuextract
A 3.8B model fine-tuned on a private high-quality synthetic dataset for information extraction, based on Phi-3.
3.8b
⬇ 530.8K indirme · 17 varyant · 07.2024
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.
2b
7b
⬇ 3.1M indirme · 85 varyant · 07.2024
codellama
A large language model that can use text prompts to generate and discuss code.
7b
13b
34b
70b
⬇ 5.9M indirme · 199 varyant · 07.2024
firefunction-v2
An open weights function calling model based on Llama 3, competitive with GPT-4o function calling capabilities.
Araç Kullanımı
70b
⬇ 515.1K indirme · 17 varyant · 07.2024
mathstral
MathΣtral: a 7B model designed for math reasoning and scientific discovery by Mistral AI.
7b
⬇ 540K indirme · 17 varyant · 07.2024
codegeex4
A versatile model for AI software development scenarios, including code completion.
9b
⬇ 681K indirme · 17 varyant · 07.2024
glm4
A strong multi-lingual general language model with competitive performance to Llama 3.
9b
⬇ 1.2M indirme · 32 varyant · 07.2024
codeqwen
CodeQwen1.5 is a large language model pretrained on a large amount of code data.
7b
⬇ 1.1M indirme · 30 varyant · 06.2024
deepseek-v2
A strong, economical, and efficient Mixture-of-Experts language model.
16b
236b
⬇ 1.2M indirme · 34 varyant · 06.2024
aya
Aya 23, released by Cohere, is a new family of state-of-the-art, multilingual models that support 23 languages.
8b
35b
⬇ 1.1M indirme · 33 varyant · 05.2024
llama3
Meta Llama 3: The most capable openly available LLM to date
8b
70b
⬇ 25M indirme · 68 varyant · 05.2024
falcon2
Falcon2 is an 11B parameters causal decoder-only model built by TII and trained over 5T tokens.
11b
⬇ 532K indirme · 17 varyant · 05.2024
yi
Yi 1.5 is a high-performing, bilingual language model.
6b
9b
34b
⬇ 1.4M indirme · 174 varyant · 05.2024
llama3-chatqa
A model from NVIDIA based on Llama 3 that excels at conversational question answering (QA) and retrieval-augmented generation (RAG).
8b
70b
⬇ 1M indirme · 35 varyant · 05.2024
dolphin-llama3
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
⬇ 2.1M indirme · 53 varyant · 05.2024
llava-phi3
A new small LLaVA model fine-tuned from Phi 3 Mini.
Görüntü
3.8b
⬇ 304.8K indirme · 4 varyant · 05.2024
moondream
moondream2 is a small vision language model designed to run efficiently on edge devices.
Görüntü
1.8b
⬇ 1.5M indirme · 18 varyant · 05.2024
llava-llama3
A LLaVA model fine-tuned from Llama 3 Instruct with better scores in several benchmarks.
Görüntü
8b
⬇ 2.3M indirme · 4 varyant · 05.2024
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
⬇ 1M indirme · 84 varyant · 05.2024
all-minilm
Embedding models on very large sentence level datasets.
Embedding
22m
33m
⬇ 3.4M indirme · 10 varyant · 05.2024
mxbai-embed-large
State-of-the-art large embedding model from mixedbread.ai
Embedding
335m
⬇ 13.5M indirme · 4 varyant · 05.2024
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