A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.
96 Pulls 5 Tags Updated 22 hours ago
OpenHands LM is built on the foundation of Qwen Coder 2.5 Instruct 32B, leveraging its powerful base capabilities for coding tasks.
113 Pulls 7 Tags Updated 3 days ago
9 Pulls 1 Tag Updated 5 days ago
gemma-3-27b-it-abliterated.q8_0.gguf
64 Pulls 1 Tag Updated 12 days ago
gemma-3-12b-it-abliterated.fp16.gguf
23 Pulls 1 Tag Updated 12 days ago
216 Pulls 3 Tags Updated 12 days ago
489 Pulls 1 Tag Updated 2 weeks ago
253 Pulls 1 Tag Updated 2 weeks ago
The current, most capable model that runs on a single GPU.
4,204 Pulls 14 Tags Updated 5 days ago
ollama run huihui_ai/deepseek-r1-abliterated:32b
Abliterated Llama 3, 3.1, 3.3
340 Pulls 7 Tags Updated 4 weeks ago
Llama 3.3 Abliterated
140 Pulls 5 Tags Updated 4 weeks ago
A compact and efficient vision-language model, specifically designed for visual document understanding, enabling automated content extraction from tables, charts, infographics, plots, diagrams, and more.
691 Pulls 5 Tags Updated 4 weeks ago
Granite-3.2 is a family of long-context AI models from IBM Granite fine-tuned for thinking capabilities.
526 Pulls 11 Tags Updated 4 weeks ago
15 Pulls 1 Tag Updated 4 weeks ago
Phi-4-mini brings significant enhancements in multilingual support, reasoning, and mathematics, and now, the long-awaited function calling feature is finally supported.
822 Pulls 5 Tags Updated 5 weeks ago
Kanana, a series of bilingual language models (developed by Kakao) that demonstrate exceeding performance in Korean and competitive performance in English.
322 Pulls 5 Tags Updated 5 weeks ago
Arcee-Blitz (24B) is a new Mistral-based 24B model distilled from DeepSeek, designed to be both fast and efficient. We view it as a practical “workhorse” model that can tackle a range of tasks without the overhead of larger architectures.
493 Pulls 5 Tags Updated 5 weeks ago
fluently-lm/FluentlyLM-Prinum
107 Pulls 5 Tags Updated 5 weeks ago
Tiny-R1-32B-Preview, which outperforms the 70B model Deepseek-R1-Distill-Llama-70B and nearly matches the full R1 model in math.
905 Pulls 6 Tags Updated 5 weeks ago