test brand new gemma4:12b-mlx on MBP via Ollama #life

try ollama 0.30 rc on macbook #life

trying Qwen 3.5 9B model from my RTX 3080 Ti running at home with Ollama exposed to VPN, remotely accessed by my Zed IDE for agentic coding from my Mac but with AI compute done on my big rig at home #life

ollama ready for temporal #thecompaniesapi

setting up ollama and qwen3.5:9b on mac mini #saasmakers #thecompaniesapi

🤖 Took my son to his basketball tournament and got my #openclaw running well on an Orange Pi Zero 2W with Ollama and Gemmi 4. Not bad.

try ollama locally with multi tool agent

Write daily: aiengineerguide.com/til/ollam… #ai

Playing with Ollama's cloud offering and it's pretty good. Waiting on a PyDantic AI update to start using it in a few projects #research

observe green memory pressure with new MacBook Pro w/ 48GB RAM, even with ollama running w/ local LLM loaded and all my apps and containers running #life

🤖 Deep dove into Ollama's hosted models to see what they can do. really, really impressive at writing and story telling. #research

#thecompaniesapi properly prioritize user jobs in front of continuous scan; monitor the queue; redeploy textsynth to handle only translation as its much faster; tune ollama config to match system resources better; improve extraction flow; cross check envs and drop old tlds in cloudflare in favor of tailscale in all our infra

#thecompaniesapi make browser rendering optional in full flow; fully deploy ollama & new models; run new flow with it; rewrite translate feature

#thecompaniesapi finish model training; convert 2 new weights to gguf and push them to HF; write ollama docker image & compose files to prepare final deployment; run first benchs locally

#thecompaniesapi optimize our extraction flow code; prepare textsynth replacement by ollama by converting our existing model to it; start fine tuning new model to support thinking

🤖 Installed and tried out GPT-OSS on Ollama. #research

trying out new gpt-oss 20B (Ollama)

Write daily: aiengineerguide.com/til/ollam… #ai

Write daily: aiengineerguide.com/til/ollam… #ai

#thecompaniesapi rebuild our dataset and prepare model retraining; setup ollama to bench it as replacement for our current inference server