Trying to help at https://discord.gg/ollama
-
fara
Fara-7B is Microsoft's first agentic small language model (SLM) designed specifically for computer use. (Template supports tools)
vision tools 7b2,705 Pulls 4 Tags Updated 2 months ago
-
LightOnOCR-2
Best OCR model. LightOnOCR-2-1B is our flagship OCR model, refined with RLVR training for maximum accuracy. We recommend this variant for most OCR tasks.
vision tools 1b1,204 Pulls 2 Tags Updated 2 weeks ago
-
AgentCPM-Explore
AgentCPM-Explore is a small, open‑source deep research model designed for long‑horizon, complex reasoning tasks on devices. (Template supports tools)
tools thinking 4b467 Pulls 1 Tag Updated 3 weeks ago
-
mai-ui
MAI-UI is a family of large-scale GUI foundation agents (2B,8B) built for real-world, interactive human-computer control across desktop and mobile Uls. (Template supports tools)
vision tools 2b 8b335 Pulls 8 Tags Updated 3 weeks ago
-
NuMarkdown-Thinking
It is the first reasoning OCR VLM. It is specifically trained to convert documents into clean Markdown files, well suited for RAG applications.
vision thinking 8b281 Pulls 2 Tags Updated 1 week ago
-
qwen2.5-coder-manim
Fine-tuned Qwen2.5-Coder-14B-Instruct model trained on 3blue1brown-manim dataset with 2,407 examples from HuggingFace.
tools150 Pulls 3 Tags Updated 3 weeks ago
-
sweep-next-edit-1.5B
Sweep Next-Edit a 1.5B parameter model for next-edit autocomplete, quantized to Q8_0 GGUF format. (Template supports tools)
tools145 Pulls 1 Tag Updated 2 weeks ago