O3 · Ollama

olmo-3

Olmo is a series of Open language models designed to enable the science of language models. These models are pre-trained on the Dolma 3 dataset and post-trained on the Dolci datasets.

tools thinking 7b 32b

453.7K Pulls 15 Tags Updated 8 months ago

olmo-3.1

Olmo is a series of Open language models designed to enable the science of language models. These models are pre-trained on the Dolma 3 dataset and post-trained on the Dolci datasets.

tools thinking 32b

287.8K Pulls 10 Tags Updated 8 months ago

deepseek-r1

DeepSeek-R1 is a family of open reasoning models with performance approaching that of leading models, such as O3 and Gemini 2.5 Pro.

tools thinking 1.5b 7b 8b 14b 32b 70b 671b

92.2M Pulls 35 Tags Updated 1 year ago

orca-mini

A general-purpose model ranging from 3 billion parameters to 70 billion, suitable for entry-level hardware.

3b 7b 13b 70b

3M Pulls 119 Tags Updated 2 years ago

deepcoder

DeepCoder is a fully open-Source 14B coder model at O3-mini level, with a 1.5B version also available.

1.5b 14b

947.7K Pulls 9 Tags Updated 1 year ago

openchat

A family of open-source models trained on a wide variety of data, surpassing ChatGPT on various benchmarks. Updated to version 3.5-0106.

7b

1.3M Pulls 50 Tags Updated 2 years ago

o3s/chatbot

93 Pulls 1 Tag Updated 2 years ago

Orvyth/engrym-seed

Open-weight local LLM ladder, 2B–27B. Agentic tool calling and thinking. Native 256K context, 32K default. Base 9B scores 91.6% (131/143, current blob). Orvyth seed-tier. Intelligence. Governed.

tools thinking

342 Pulls 18 Tags Updated 2 weeks ago

OpenNix/wazuh-llama-3.1-8B-v1

LLaMA 3.1 8B Instruct model fine-tuned for advanced Wazuh security log analysis with instruction-following capabilities

628 Pulls 1 Tag Updated 11 months ago

OpenNix/aws-security-assistant

LLaMA 3.1 8B Instruct model fine-tuned for AWS cloud security event analysis.

125 Pulls 1 Tag Updated 10 months ago

OpenNix/wazuh-llama-3.1-8B-base

LLaMA 3.1 8B Instruct model fine-tuned for advanced Wazuh security log analysis with instruction-following capabilities.

101 Pulls 1 Tag Updated 11 months ago

OdaxAI_00/dante-mosaic-3.5b

2 Pulls 1 Tag Updated 3 months ago

oamazonasgabriel/qwen3.8-27b

Qwen3.8-27B in Q4_K_M quantization (32GB+ VRAM required). Dense 27.8B parameters with hybrid attention for long context (256K tokens). Apache 2.0 license. Ideal for high-VRAM setups (RTX 5090/4090 dual, M4 Ultra, etc.).

787 Pulls 3 Tags Updated 3 days ago

odytrice/qwen3.8

Qwen 3.8 Ollama profiles for RTX 5090 27B with vision, thinking mode, and native tool calling

vision tools thinking

410 Pulls 2 Tags Updated 2 weeks ago

oamazonasgabriel/nemotron-3.5-lightning

An open 30B MoE model with ~3B active parameters, packaged by impacte.tech for the execution layer of always-on agents. Uses the official Q4_K_M / IQ4_XS quantizations. Features native tool calling and thinking modes.

tools thinking

79 Pulls 2 Tags Updated 1 week ago

oamazonasgabriel/qwen3.6-35b-a3b

A memory-efficient model configuration of Qwen3.6-35B-A3B using an upstream imatrix-calibrated IQ4_XS quantization and q4_0 KV cache. Designed for 24 GB VRAM

tools thinking

2,022 Pulls 1 Tag Updated 2 months ago

odytrice/muse

Meta's Apache 2.0 agentic vision-language model, 30B at 4-bit with 131K context

vision 30b

17 Pulls 2 Tags Updated yesterday

odytrice/qwen3.6

Qwen 3.6 Ollama profiles for RTX 5090 across 27B dense and 35B-A3B MoE variants, with vision, thinking mode, and native tool calling.

vision tools thinking

813 Pulls 3 Tags Updated 2 months ago

odytrice/gemma4

Gemma 4 Ollama profiles for RTX 4090/5090 across 12B, 26B-A4B, and 31B variants, with multimodal support and native tool calling

vision tools thinking

476 Pulls 5 Tags Updated 2 months ago

oamazonasgabriel/qwen2.5-coder.1.5b-mlx

Code-specialized 1.5B model in F16 precision, optimized for MLX workflows. 32K context, fill-in-the-middle support, and fast inference on GPUs with 8 GB+ memory. Ideal for code generation, completion, and bug fixing.

173 Pulls 1 Tag Updated 1 month ago