Mistral Small 3
First 5090 LLM results, compared to 4090 and 6000 ada
Deepseek R1 GGUFs are up in Ollama library
Outperforming Llama 70B with Llama 3B on hard math by scaling test-time compute!
Ollama now official supports llama 3.2 vision
Pushing power into the grid with Ioniq 5
Official Thread: ADCC 2022
B450 Tomahawk + 3600 seemingly successful
