functiongemma
FunctionGemma is a specialized version of Google's Gemma 3 270M model fine-tuned explicitly for function calling.
⬇ 180K indirme · 4 varyant · 12.2025
Kendi bilgisayarınızda veya sunucunuzda ücretsiz çalıştırabileceğiniz modeller. Katalog ollama.com kütüphanesiyle canlı senkrondur · Son senkron: 13.08.2026 22:48.
233 model
FunctionGemma is a specialized version of Google's Gemma 3 270M model fine-tuned explicitly for function calling.
⬇ 180K indirme · 4 varyant · 12.2025
gpt-oss-safeguard-20b and gpt-oss-safeguard-120b are safety reasoning models built-upon gpt-oss
⬇ 150.8K indirme · 3 varyant · 10.2025
An open 30B MoE model from NVIDIA with 3B activated parameters that delivers strong reasoning and agentic capabilities.
⬇ 140.9K indirme · 3 varyant · 03.2026
MedGemma 1.5 4B is an updated version of the MedGemma 4B model.
⬇ 125.6K indirme · 5 varyant · 04.2026
LFM2.5-8B-A1B, an edge model built for fast, reliable tool calling on consumer hardware.
⬇ 114K indirme · 5 varyant · 05.2026
A general-purpose multimodal mixture-of-experts model for production-grade tasks and enterprise workloads.
⬇ 90.1K indirme · 0 varyant · 12.2025
Laguna XS 2.1 is a 33B total parameter Mixture-of-Experts model with 3B activated parameters per token designed for agentic coding and long-horizon work on a local machine.
⬇ 89.4K indirme · 7 varyant · 07.2026
Our most capable model to date, designed for long-horizon work. 70.2% on Terminal-Bench 2.1 at 118B-A8B.
⬇ 74.7K indirme · 7 varyant · 07.2026
Meta's latest open model built for always-on local agents. 30B parameters, licensed under Apache 2.0 and runs on a single GPU — tuned for tool use, long tasks, and failure recovery.
⬇ 62.2K indirme · 15 varyant · 08.2026
NVIDIA Nemotron 3 Ultra is built for high-throughput reasoning and long-running agent workflows.
⬇ 47K indirme · 0 varyant · 06.2026
North Mini Code is Cohere's first model for developers — a 30B Mixture-of-Experts model with 3B active parameters, built for agentic software engineering.
⬇ 40.1K indirme · 7 varyant · 06.2026
Kimi K3 is an open-weight, native multimodal agentic model and our most capable model to date.
⬇ 35.3K indirme · 0 varyant · 07.2026
A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone
⬇ 32.4K indirme · 13 varyant · 06.2026
A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone
⬇ 25.4K indirme · 13 varyant · 06.2026
Laguna XS.2 is a 33B total parameter Mixture-of-Experts model with 3B activated parameters per token designed for agentic coding and long-horizon work on a local machine.
⬇ 25.1K indirme · 7 varyant · 07.2026
NVIDIA Nemotron 3.5 Lightning is an open 30B mixture-of-experts (MoE) model with 3B active parameters built for always-on agents.
⬇ 21.1K indirme · 11 varyant · 08.2026
Granite Guardian 4.1 is a specialized safety and judging model from IBM Research that evaluates whether LLM prompts and responses meet specified harm criteria.
⬇ 8,830 indirme · 16 varyant · 06.2026
Bu modeller Ollama ile tek komutla bilgisayarınızda çalışır (Windows, macOS, Linux). Verileriniz cihazınızdan çıkmaz — gizlilik gerektiren işler için idealdir.
ollama run … komutunu terminale yapıştırın