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 7b4,070 Pulls 4 Tags Updated 3 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 1b2,785 Pulls 2 Tags Updated 2 months ago
-
lfm2
LFM2-8B-A1B is the best on-device MoE in terms of both quality (comparable to 3-4B dense models) and speed (faster than Qwen3-1.7B).
tools 8b699 Pulls 4 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 4b625 Pulls 1 Tag Updated 2 months 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 8b571 Pulls 8 Tags Updated 2 months 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 8b464 Pulls 2 Tags Updated 1 month ago
-
Qianfan-OCR
Qianfan-OCR is a 4B VL model that replaces multi-step OCR pipelines with a single system, enabling direct image-to-Markdown conversion and advanced document understanding.
vision tools thinking 4b453 Pulls 3 Tags Updated 1 week ago
-
manim-coder
Fine-tuned manim model using Qwen2.5-Coder-14B-Instruct trained on 3blue1brown-manim dataset with 2,407 examples.
tools 14b262 Pulls 3 Tags Updated 1 month 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)
tools229 Pulls 1 Tag Updated 2 months ago
-
strand-rust-coder
The model fine-tunes Qwen2.5-Coder-14B for Rust-specific programming tasks using a 191K-example synthetic dataset built via multi-model generation and peer-reviewed validation.
tools 14b228 Pulls 3 Tags Updated 1 month ago
-
context-1
Context-1 is a 20B agentic search model that breaks complex queries into steps, retrieves relevant info iteratively, and manages its context to support multi-hop reasoning alongside a larger model.
tools thinking 20b6 Pulls 3 Tags Updated 20 hours ago