User: robertkarl

• Created: 5372 days ago
• Karma: 100
• I'm working on local LLM inference. I want to save money on my Claude/Codex bill by having my Mac do it. I like Qwen for this.

  I'm working on glass-slipper.cc (no telemetry; no login; just local offload from Claude to dumb model).

  email: robertkarljr at the big google-provided email one.

submissions | comments