ai testing
-
Proxmox
Qwen QwQ 2.5 32B Ollama Local AI Server Benchmarked w/ Cuda vs Apple M4 MLX
The new Qwen with Questions aka QwQ LLM fine tune based off the popular Qwen 2.5 32B base is a unique step in chain of though and reasoning which really is impressive! I was lucky enough to find some stats from a X poster about their Apple Q8 M4 Max Tokens per second also to compare against for all those…
Read More » -
Proxmox
Local Ai Models on Quadro P2000 – Homelab testing Gemma Ai, Qwen2, Smollm, Phi 3.5, Llama 3.1
Longtime homelab favorite Quadro 2000 is a 5 GB GPU that is still pretty decent and in a lot of home servers already, but how does it handle running local LLMs? This is crazy, but it works and the performance IS NOT what you expect. Must watch if you have P2000 already in your system! I will cover some tips…
Read More »
