Holo-3.1 vision-language computer-use agents by H Company. Locate UI elements and drive web, desktop & mobile automation from a screenshot — returns clicks in normalized [0,1000] coords. 0.8B & 4B, instruct & thinking variants, Q4_K_M/Q8_0. Apache 2.0.
758 Pulls 7 Tags Updated 1 month ago
Holo1 is an Action Vision-Language Model (VLM) developed by HCompany for use in the Surfer-H web agent system.
274 Pulls 3 Tags Updated 1 year ago
hoodaAgents is a local-first AI assistant framework designed to run customizable AI agents entirely on your machine using Ollama and LangGraph. It integrates powerful open-source LLMs (like Mistral) with intelligent tool usage.
1 Pull 1 Tag Updated 3 days ago
35 Pulls 1 Tag Updated 5 months ago
27 Pulls 1 Tag Updated 9 months ago
3 Pulls 1 Tag Updated 2 months ago
2 Pulls 1 Tag Updated 2 months ago
19 Pulls 1 Tag Updated 1 year ago
16 Pulls 1 Tag Updated 1 year ago
Buddy is a fast, direct Llama 3 8B-based assistant optimized for quick answers, shell command generation, and low-friction daily technical work.
51 Pulls 1 Tag Updated 3 months ago
108 Pulls 1 Tag Updated 10 months ago
51 Pulls 1 Tag Updated 10 months ago
Indonesian Sovereign AI Model (Tactical 1.5B). Forged by AetherAI for lightning-fast, offline, and privacy-first local reasoning in formal Bahasa Indonesia.
3 Pulls 1 Tag Updated 1 month ago
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. This version of Qwen3 is optimized for direct, concise responses without thinking.
4,509 Pulls 5 Tags Updated 1 year ago
ollama push ThiagoAlbuquerque/Holly-Juridico
19 Pulls 1 Tag Updated 10 months ago
Homer Simpson is the bumbling, loveable, and often clueless patriarch of the Simpson family. Fond of beer, donuts, and naps, he stumbles through life with good intentions but frequent mishaps.
33 Pulls 1 Tag Updated 1 year ago
abideen/MonarchCoder-7B (https://github.com/ollama/ollama/blob/main/docs/import.md)
10 Pulls 2 Tags Updated 2 years ago
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.
1.1M Pulls 6 Tags Updated 5 months ago
NVIDIA Nemotron 3 Ultra is built for high-throughput reasoning and long-running agent workflows.
48.8K Pulls 1 Tag Updated 2 months ago
LFM2.5 is a new family of hybrid models designed for on-device deployment.
1.3M Pulls 5 Tags Updated 6 months ago