mathstral
MathΣtral: a 7B model designed for math reasoning and scientific discovery by Mistral AI.
7b
⬇ 540K indirme · 17 varyant · 07.2024
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
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
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
notus
A 7B chat model fine-tuned with high-quality data and based on Zephyr.
7b
⬇ 530.8K indirme · 18 varyant · 12.2023
notux
A top-performing mixture of experts model, fine-tuned with high-quality data.
8x7b
⬇ 529.6K indirme · 18 varyant · 12.2023
stablelm-zephyr
A lightweight chat model allowing accurate, and responsive output without requiring high-end hardware.
3b
⬇ 524.3K indirme · 17 varyant · 12.2023
bespoke-minicheck
A state-of-the-art fact-checking model developed by Bespoke Labs.
7b
⬇ 519.7K indirme · 17 varyant · 09.2024
duckdb-nsql
7B parameter text-to-SQL model made by MotherDuck and Numbers Station.
7b
⬇ 518.8K indirme · 17 varyant · 01.2024
mistrallite
MistralLite is a fine-tuned model based on Mistral with enhanced capabilities of processing long contexts.
7b
⬇ 515.5K indirme · 17 varyant · 11.2023
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
deepseek-ocr
DeepSeek-OCR is a vision-language model that can perform token-efficient OCR.
Görüntü
3b
⬇ 511.6K indirme · 3 varyant · 11.2025
wizard-vicuna
Wizard Vicuna is a 13B parameter model based on Llama 2 trained by MelodysDreamj.
13b
⬇ 509.4K indirme · 17 varyant · 10.2023
open-orca-platypus2
Merge of the Open Orca OpenChat model and the Garage-bAInd Platypus 2 model. Designed for chat and code generation.
13b
⬇ 501.8K indirme · 17 varyant · 10.2023
rnj-1
Rnj-1 is a family of 8B parameter open-weight, dense models trained from scratch by Essential AI, optimized for code and STEM with capabilities on par with SOTA open-weight models.
Araç Kullanımı
8b
⬇ 501.7K indirme · 5 varyant · 12.2025
codebooga
A high-performing code instruct model created by merging two existing code models.
34b
⬇ 492.4K indirme · 16 varyant · 10.2023
goliath
A language model created by combining two fine-tuned Llama 2 70B models into one.
⬇ 471.2K indirme · 16 varyant · 11.2023
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
olmo-3
Olmo is a series of Open language models designed to enable the science of language models. These models are pre-trained on the Dolma 3 dataset and post-trained on the Dolci datasets.
Araç Kullanımı
Akıl Yürütme
7b
32b
⬇ 448.5K indirme · 15 varyant · 12.2025
snowflake-arctic-embed2
Snowflake's frontier embedding model. Arctic Embed 2.0 adds multilingual support without sacrificing English performance or scalability.
Embedding
568m
⬇ 439K indirme · 3 varyant · 12.2024
kimi-k2.6
Kimi K2.6 is an open-source, native multimodal agentic model that advances practical capabilities in long-horizon coding, coding-driven design, proactive autonomous execution, and swarm-based task orchestration.
Görüntü
Araç Kullanımı
Akıl Yürütme
⬇ 430.4K indirme · 0 varyant · 04.2026
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
sailor2
Sailor2 are multilingual language models made for South-East Asia. Available in 1B, 8B, and 20B parameter sizes.
1b
8b
20b
⬇ 406.4K indirme · 13 varyant · 12.2024
minimax-m3
MiniMax M3: Coding & Agentic Frontier. 1M context window. Native Multimodality.
Görüntü
Araç Kullanımı
Akıl Yürütme
⬇ 406.4K indirme · 0 varyant · 06.2026
tulu3
Tülu 3 is a leading instruction following model family, offering fully open-source data, code, and recipes by the The Allen Institute for AI.
8b
70b
⬇ 383.3K indirme · 9 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