| Cloud models |
- |
Sep 19, 2025 |
330 |
- |
| Secure Minions: private collaboration between Ollama and frontier models |
- |
Jun 03, 2025 |
665 |
- |
| OpenAI gpt-oss |
- |
Aug 05, 2025 |
415 |
- |
| Reduce hallucinations with Bespoke-Minicheck |
- |
Sep 18, 2024 |
302 |
- |
| OpenAI compatibility |
- |
Feb 08, 2024 |
423 |
- |
| Llama 3.2 Vision |
- |
Nov 06, 2024 |
199 |
- |
| An entirely open-source AI code assistant inside your editor |
- |
May 31, 2024 |
885 |
- |
| Ollama's new engine for multimodal models |
- |
May 15, 2025 |
1447 |
- |
| Thinking |
- |
May 30, 2025 |
698 |
- |
| IBM Granite 3.0 models |
- |
Oct 21, 2024 |
210 |
- |
| Minions: where local and cloud LLMs meet |
- |
Feb 25, 2025 |
672 |
- |
| New coding models & integrations |
- |
Oct 16, 2025 |
439 |
- |
| Web search |
- |
Sep 24, 2025 |
1100 |
- |
| MiniMax M2 |
- |
Oct 28, 2025 |
460 |
- |
| Ollama's new app |
- |
Jul 30, 2025 |
133 |
- |
| Embedding models |
- |
Apr 08, 2024 |
622 |
- |
| NVIDIA DGX Spark performance |
- |
Oct 23, 2025 |
400 |
- |
| Python & JavaScript Libraries |
- |
Jan 23, 2024 |
304 |
- |
| Structured outputs |
- |
Dec 06, 2024 |
844 |
- |
| Windows preview |
- |
Feb 15, 2024 |
268 |
- |
| Qwen3-VL |
- |
Oct 14, 2025 |
547 |
- |
| OpenAI gpt-oss-safeguard |
- |
Oct 29, 2025 |
457 |
- |
| New model scheduling |
- |
Sep 23, 2025 |
297 |
- |
| Ollama Python library 0.4 with function calling improvements |
- |
Nov 25, 2024 |
452 |
- |
| Google announces Firebase Genkit with Ollama support |
- |
May 20, 2024 |
125 |
- |
| Ollama now supports AMD graphics cards |
- |
Mar 14, 2024 |
133 |
- |
| Vision models |
- |
Feb 02, 2024 |
418 |
- |
| Llama 3 is not very censored |
- |
Apr 19, 2024 |
577 |
- |
| Streaming responses with tool calling |
- |
May 28, 2025 |
1059 |
- |
| Llama 3 |
- |
Apr 18, 2024 |
187 |
- |
| Tool support |
- |
Jul 25, 2024 |
312 |
- |
| NVIDIA DGX Spark |
- |
Oct 13, 2025 |
145 |
- |
| Llama 3.2 goes small and multimodal |
- |
Sep 25, 2024 |
166 |
- |
| Google Gemma 2 |
- |
Jun 27, 2024 |
127 |
- |