https://ollama.com/search?o=newest Model Library 2026-04-12T06:53:45.589603+00:00 https://ollama.com/library/glm-5.1

GLM-5.1 is our next-generation flagship model for agentic engineering, with significantly stronger coding capabilities than its predecessor. It achieves state-of-the-art performance on SWE-Bench Pro and leads GLM-5 by a wide margin.

2026-04-07T15:00:00+00:00 <p>GLM-5.1 is our next-generation flagship model for agentic engineering, with significantly stronger coding capabilities than its predecessor. It achieves state-of-the-art performance on SWE-Bench Pro and leads GLM-5 by a wide margin.</p><p>Pulls: 24.4K</p><p>Tags: 1</p> https://ollama.com/library/gemma4

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.

2026-04-06T01:39:00+00:00 <p>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.</p><p>Pulls: 2.5M</p><p>Tags: 17</p> https://ollama.com/library/qwen3.5

Qwen 3.5 is a family of open-source multimodal models that delivers exceptional utility and performance.

2026-04-01T23:10:00+00:00 <p>Qwen 3.5 is a family of open-source multimodal models that delivers exceptional utility and performance.</p><p>Pulls: 5.8M</p><p>Tags: 58</p> https://ollama.com/library/nemotron-cascade-2

An open 30B MoE model from NVIDIA with 3B activated parameters that delivers strong reasoning and agentic capabilities.

2026-03-20T20:10:00+00:00 <p>An open 30B MoE model from NVIDIA with 3B activated parameters that delivers strong reasoning and agentic capabilities.</p><p>Pulls: 89K</p><p>Tags: 3</p> https://ollama.com/library/minimax-m2.7

MiniMax's M2-series model for coding, agentic workflows, and professional productivity.

2026-03-18T18:05:00+00:00 <p>MiniMax's M2-series model for coding, agentic workflows, and professional productivity.</p><p>Pulls: 65.2K</p><p>Tags: 1</p> https://ollama.com/library/nemotron-3-nano

Nemotron-3-Nano is a new Standard for Efficient, Open, and Intelligent Agentic Models, now updated with a 4B parameter count model.

2026-03-16T15:34:00+00:00 <p>Nemotron-3-Nano is a new Standard for Efficient, Open, and Intelligent Agentic Models, now updated with a 4B parameter count model.</p><p>Pulls: 383.7K</p><p>Tags: 9</p> https://ollama.com/library/nemotron-3-super

NVIDIA Nemotron 3 Super is a 120B open MoE model activating just 12B parameters to deliver maximum compute efficiency and accuracy for complex multi-agent applications.

2026-03-11T16:00:00+00:00 <p>NVIDIA Nemotron 3 Super is a 120B open MoE model activating just 12B parameters to deliver maximum compute efficiency and accuracy for complex multi-agent applications.</p><p>Pulls: 223K</p><p>Tags: 7</p> https://ollama.com/library/lfm2

LFM2 is a family of hybrid models designed for on-device deployment. LFM2-24B-A2B is the largest model in the family, scaling the architecture to 24 billion parameters while keeping inference efficient.

2026-02-24T01:17:00+00:00 <p>LFM2 is a family of hybrid models designed for on-device deployment. LFM2-24B-A2B is the largest model in the family, scaling the architecture to 24 billion parameters while keeping inference efficient.</p><p>Pulls: 1.1M</p><p>Tags: 6</p> https://ollama.com/library/minimax-m2.5

MiniMax-M2.5 is a state-of-the-art large language model designed for real-world productivity and coding tasks.

2026-02-12T09:22:00+00:00 <p>MiniMax-M2.5 is a state-of-the-art large language model designed for real-world productivity and coding tasks.</p><p>Pulls: 159.9K</p><p>Tags: 1</p> https://ollama.com/library/glm-5

A strong reasoning and agentic model from Z.ai with 744B total parameters (40B active), built for complex systems engineering and long-horizon tasks.

2026-02-11T18:43:00+00:00 <p>A strong reasoning and agentic model from Z.ai with 744B total parameters (40B active), built for complex systems engineering and long-horizon tasks.</p><p>Pulls: 181.7K</p><p>Tags: 1</p> https://ollama.com/library/qwen3-coder-next

Qwen3-Coder-Next is a coding-focused language model from Alibaba's Qwen team, optimized for agentic coding workflows and local development.

2026-02-06T05:23:00+00:00 <p>Qwen3-Coder-Next is a coding-focused language model from Alibaba's Qwen team, optimized for agentic coding workflows and local development.</p><p>Pulls: 1M</p><p>Tags: 4</p> https://ollama.com/library/glm-ocr

GLM-OCR is a multimodal OCR model for complex document understanding, built on the GLM-V encoder–decoder architecture.

2026-02-02T23:29:00+00:00 <p>GLM-OCR is a multimodal OCR model for complex document understanding, built on the GLM-V encoder–decoder architecture.</p><p>Pulls: 247K</p><p>Tags: 3</p> https://ollama.com/library/kimi-k2.5

Kimi K2.5 is an open-source, native multimodal agentic model that seamlessly integrates vision and language understanding with advanced agentic capabilities, instant and thinking modes, as well as conversational and agentic paradigms.

2026-01-27T07:29:00+00:00 <p>Kimi K2.5 is an open-source, native multimodal agentic model that seamlessly integrates vision and language understanding with advanced agentic capabilities, instant and thinking modes, as well as conversational and agentic paradigms.</p><p>Pulls: 236.2K</p><p>Tags: 1</p> https://ollama.com/library/glm-4.7-flash

As the strongest model in the 30B class, GLM-4.7-Flash offers a new option for lightweight deployment that balances performance and efficiency.

2026-01-24T23:40:00+00:00 <p>As the strongest model in the 30B class, GLM-4.7-Flash offers a new option for lightweight deployment that balances performance and efficiency.</p><p>Pulls: 1.1M</p><p>Tags: 4</p> https://ollama.com/library/lfm2.5-thinking

LFM2.5 is a new family of hybrid models designed for on-device deployment.

2026-01-20T12:41:00+00:00 <p>LFM2.5 is a new family of hybrid models designed for on-device deployment.</p><p>Pulls: 1.1M</p><p>Tags: 5</p> https://ollama.com/library/translategemma

A new collection of open translation models built on Gemma 3, helping people communicate across 55 languages.

2026-01-16T20:57:00+00:00 <p>A new collection of open translation models built on Gemma 3, helping people communicate across 55 languages.</p><p>Pulls: 1.1M</p><p>Tags: 13</p> https://ollama.com/library/glm-4.7

Advancing the Coding Capability

2025-12-23T17:56:00+00:00 <p>Advancing the Coding Capability</p><p>Pulls: 87.8K</p><p>Tags: 1</p> https://ollama.com/library/minimax-m2.1

Exceptional multilingual capabilities to elevate code engineering

2025-12-23T03:19:00+00:00 <p>Exceptional multilingual capabilities to elevate code engineering</p><p>Pulls: 38.8K</p><p>Tags: 1</p> https://ollama.com/library/gemini-3-flash-preview

Gemini 3 Flash offers frontier intelligence built for speed at a fraction of the cost.

2025-12-20T20:44:00+00:00 <p>Gemini 3 Flash offers frontier intelligence built for speed at a fraction of the cost.</p><p>Pulls: 129.1K</p><p>Tags: 2</p> https://ollama.com/library/functiongemma

FunctionGemma is a specialized version of Google's Gemma 3 270M model fine-tuned explicitly for function calling.

2025-12-18T07:03:00+00:00 <p>FunctionGemma is a specialized version of Google's Gemma 3 270M model fine-tuned explicitly for function calling.</p><p>Pulls: 144.3K</p><p>Tags: 4</p>