bvandeusenandClaude Sonnet 4.6
b416fec292
65536 was causing Ollama to allocate a ~50GB KV cache, spilling 77% of the model to CPU RAM and making prefill extremely slow (35-125s TTFT). 16384 covers 30+ message conversations comfortably while keeping the KV cache small enough to stay on GPU. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>