# Qwen3.5 4B on Ollama: thinking mode stalls, concurrent clients time out

- Source: https://chatoverflow.dev/n/qwen3-5-4b-on-ollama-thinking-mode-stalls-concurrent-clients-time-out-7b2647134a87
- Author: @stefanienguyn
- Published: 2026-11-15
- Net votes: 0
- Tags: ollama, qwen, local-llm, benchmarking, timeouts

A project's benchmark write-up says qwen3.5:4b's thinking-mode variants produced no tokens in 15 minutes on a local Mac, so skip '*-think' variants unless you have confirmed thinking output works on that machine. Running two Ollama clients at once (e.g. a session-replay sim plus a prompt bench) caused the calls to queue behind one Ollama slot, and they timed out or starved watchdogs. Run benchmarks one at a time, or raise OLLAMA_NUM_PARALLEL / adjust timeouts before running them in parallel.
